[{"doi":"10.1364/OE.427424","date_updated":"2023-06-16T06:56:27Z","volume":29,"author":[{"first_name":"Christian","id":"13256","full_name":"Kress, Christian","last_name":"Kress"},{"last_name":"Bahmanian","full_name":"Bahmanian, Meysam","id":"69233","first_name":"Meysam"},{"last_name":"Schwabe","id":"39217","full_name":"Schwabe, Tobias","first_name":"Tobias"},{"first_name":"J. Christoph","last_name":"Scheytt","orcid":"https://orcid.org/0000-0002-5950-6618","id":"37144","full_name":"Scheytt, J. Christoph"}],"page":"23671–23681","intvolume":"        29","citation":{"ieee":"C. Kress, M. Bahmanian, T. Schwabe, and J. C. Scheytt, “Analysis of the effects of jitter, relative intensity noise, and nonlinearity on a photonic digital-to-analog converter based on optical Nyquist pulse synthesis,” <i>Opt. Express</i>, vol. 29, no. 15, pp. 23671–23681, 2021, doi: <a href=\"https://doi.org/10.1364/OE.427424\">10.1364/OE.427424</a>.","chicago":"Kress, Christian, Meysam Bahmanian, Tobias Schwabe, and J. Christoph Scheytt. “Analysis of the Effects of Jitter, Relative Intensity Noise, and Nonlinearity on a Photonic Digital-to-Analog Converter Based on Optical Nyquist Pulse Synthesis.” <i>Opt. Express</i> 29, no. 15 (2021): 23671–23681. <a href=\"https://doi.org/10.1364/OE.427424\">https://doi.org/10.1364/OE.427424</a>.","ama":"Kress C, Bahmanian M, Schwabe T, Scheytt JC. Analysis of the effects of jitter, relative intensity noise, and nonlinearity on a photonic digital-to-analog converter based on optical Nyquist pulse synthesis. <i>Opt Express</i>. 2021;29(15):23671–23681. doi:<a href=\"https://doi.org/10.1364/OE.427424\">10.1364/OE.427424</a>","mla":"Kress, Christian, et al. “Analysis of the Effects of Jitter, Relative Intensity Noise, and Nonlinearity on a Photonic Digital-to-Analog Converter Based on Optical Nyquist Pulse Synthesis.” <i>Opt. Express</i>, vol. 29, no. 15, OSA, 2021, pp. 23671–23681, doi:<a href=\"https://doi.org/10.1364/OE.427424\">10.1364/OE.427424</a>.","short":"C. Kress, M. Bahmanian, T. Schwabe, J.C. Scheytt, Opt. Express 29 (2021) 23671–23681.","bibtex":"@article{Kress_Bahmanian_Schwabe_Scheytt_2021, title={Analysis of the effects of jitter, relative intensity noise, and nonlinearity on a photonic digital-to-analog converter based on optical Nyquist pulse synthesis}, volume={29}, DOI={<a href=\"https://doi.org/10.1364/OE.427424\">10.1364/OE.427424</a>}, number={15}, journal={Opt. Express}, publisher={OSA}, author={Kress, Christian and Bahmanian, Meysam and Schwabe, Tobias and Scheytt, J. Christoph}, year={2021}, pages={23671–23681} }","apa":"Kress, C., Bahmanian, M., Schwabe, T., &#38; Scheytt, J. C. (2021). Analysis of the effects of jitter, relative intensity noise, and nonlinearity on a photonic digital-to-analog converter based on optical Nyquist pulse synthesis. <i>Opt. Express</i>, <i>29</i>(15), 23671–23681. <a href=\"https://doi.org/10.1364/OE.427424\">https://doi.org/10.1364/OE.427424</a>"},"related_material":{"link":[{"relation":"confirmation","url":"https://pubmed.ncbi.nlm.nih.gov/34614628/"}]},"_id":"29204","project":[{"_id":"302","name":"PONyDAC: PONyDAC II - Präziser Optischer Nyquist-Puls-Synthesizer DAC","grant_number":"403154102"},{"grant_number":"13N14882","name":"NyPhE: NyPhE - Nyquist Silicon Photonics Engine","_id":"299"}],"department":[{"_id":"58"},{"_id":"230"}],"user_id":"13256","status":"public","type":"journal_article","title":"Analysis of the effects of jitter, relative intensity noise, and nonlinearity on a photonic digital-to-analog converter based on optical Nyquist pulse synthesis","publisher":"OSA","date_created":"2022-01-10T11:51:47Z","year":"2021","issue":"15","keyword":["Analog to digital converters","Diode lasers","Laser sources","Phase noise","Signal processing","Wavelength division multiplexers"],"language":[{"iso":"eng"}],"abstract":[{"lang":"eng","text":"An analysis of an optical Nyquist pulse synthesizer using Mach-Zehnder modulators is presented. The analysis allows to predict the upper limit of the effective number of bits of this type of photonic digital-to-analog converter. The analytical solution has been verified by means of electro-optic simulations. With this analysis the limiting factor for certain scenarios: relative intensity noise, distortions by driving the Mach-Zehnder modulator, or the signal generator phase noise can quickly be identified."}],"publication":"Opt. Express"},{"related_material":{"link":[{"relation":"supplementary_material","description":"Poster","url":"https://groups.uni-paderborn.de/nt/pubs/2015/ChHa15_Poster.pdf"}]},"year":"2015","citation":{"chicago":"Chinaev, Aleksej, and Reinhold Haeb-Umbach. “On Optimal Smoothing in Minimum Statistics Based Noise Tracking.” In <i>Interspeech 2015</i>, 1785–89, 2015.","ieee":"A. Chinaev and R. Haeb-Umbach, “On Optimal Smoothing in Minimum Statistics Based Noise Tracking,” in <i>Interspeech 2015</i>, 2015, pp. 1785–1789.","ama":"Chinaev A, Haeb-Umbach R. On Optimal Smoothing in Minimum Statistics Based Noise Tracking. In: <i>Interspeech 2015</i>. ; 2015:1785-1789.","apa":"Chinaev, A., &#38; Haeb-Umbach, R. (2015). On Optimal Smoothing in Minimum Statistics Based Noise Tracking. In <i>Interspeech 2015</i> (pp. 1785–1789).","mla":"Chinaev, Aleksej, and Reinhold Haeb-Umbach. “On Optimal Smoothing in Minimum Statistics Based Noise Tracking.” <i>Interspeech 2015</i>, 2015, pp. 1785–89.","short":"A. Chinaev, R. Haeb-Umbach, in: Interspeech 2015, 2015, pp. 1785–1789.","bibtex":"@inproceedings{Chinaev_Haeb-Umbach_2015, title={On Optimal Smoothing in Minimum Statistics Based Noise Tracking}, booktitle={Interspeech 2015}, author={Chinaev, Aleksej and Haeb-Umbach, Reinhold}, year={2015}, pages={1785–1789} }"},"page":"1785-1789","oa":"1","date_updated":"2022-01-06T06:51:08Z","date_created":"2019-07-12T05:27:19Z","author":[{"first_name":"Aleksej","full_name":"Chinaev, Aleksej","last_name":"Chinaev"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold"}],"title":"On Optimal Smoothing in Minimum Statistics Based Noise Tracking","main_file_link":[{"open_access":"1","url":"https://groups.uni-paderborn.de/nt/pubs/2015/ChHa15.pdf"}],"type":"conference","publication":"Interspeech 2015","abstract":[{"lang":"eng","text":"Noise tracking is an important component of speech enhancement algorithms. Of the many noise trackers proposed, Minimum Statistics (MS) is a particularly popular one due to its simple parameterization and at the same time excellent performance. In this paper we propose to further reduce the number of MS parameters by giving an alternative derivation of an optimal smoothing constant. At the same time the noise tracking performance is improved as is demonstrated by experiments employing speech degraded by various noise types and at different SNR values."}],"status":"public","_id":"11739","user_id":"44006","department":[{"_id":"54"}],"keyword":["speech enhancement","noise tracking","optimal smoothing"],"language":[{"iso":"eng"}]},{"title":"Unsupervised adaptation of a denoising autoencoder by Bayesian Feature Enhancement for reverberant asr under mismatch conditions","main_file_link":[{"url":"https://groups.uni-paderborn.de/nt/pubs/2015/hey_icassp_2015.pdf","open_access":"1"}],"doi":"10.1109/ICASSP.2015.7178933","date_updated":"2022-01-06T06:51:09Z","oa":"1","author":[{"first_name":"Jahn","full_name":"Heymann, Jahn","id":"9168","last_name":"Heymann"},{"last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242","first_name":"Reinhold"},{"full_name":"Golik, P.","last_name":"Golik","first_name":"P."},{"first_name":"R.","full_name":"Schlueter, R.","last_name":"Schlueter"}],"date_created":"2019-07-12T05:28:45Z","year":"2015","citation":{"apa":"Heymann, J., Haeb-Umbach, R., Golik, P., &#38; Schlueter, R. (2015). Unsupervised adaptation of a denoising autoencoder by Bayesian Feature Enhancement for reverberant asr under mismatch conditions. In <i>Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on</i> (pp. 5053–5057). <a href=\"https://doi.org/10.1109/ICASSP.2015.7178933\">https://doi.org/10.1109/ICASSP.2015.7178933</a>","short":"J. Heymann, R. Haeb-Umbach, P. Golik, R. Schlueter, in: Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference On, 2015, pp. 5053–5057.","bibtex":"@inproceedings{Heymann_Haeb-Umbach_Golik_Schlueter_2015, title={Unsupervised adaptation of a denoising autoencoder by Bayesian Feature Enhancement for reverberant asr under mismatch conditions}, DOI={<a href=\"https://doi.org/10.1109/ICASSP.2015.7178933\">10.1109/ICASSP.2015.7178933</a>}, booktitle={Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on}, author={Heymann, Jahn and Haeb-Umbach, Reinhold and Golik, P. and Schlueter, R.}, year={2015}, pages={5053–5057} }","mla":"Heymann, Jahn, et al. “Unsupervised Adaptation of a Denoising Autoencoder by Bayesian Feature Enhancement for Reverberant Asr under Mismatch Conditions.” <i>Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference On</i>, 2015, pp. 5053–57, doi:<a href=\"https://doi.org/10.1109/ICASSP.2015.7178933\">10.1109/ICASSP.2015.7178933</a>.","ama":"Heymann J, Haeb-Umbach R, Golik P, Schlueter R. Unsupervised adaptation of a denoising autoencoder by Bayesian Feature Enhancement for reverberant asr under mismatch conditions. In: <i>Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference On</i>. ; 2015:5053-5057. doi:<a href=\"https://doi.org/10.1109/ICASSP.2015.7178933\">10.1109/ICASSP.2015.7178933</a>","chicago":"Heymann, Jahn, Reinhold Haeb-Umbach, P. Golik, and R. Schlueter. “Unsupervised Adaptation of a Denoising Autoencoder by Bayesian Feature Enhancement for Reverberant Asr under Mismatch Conditions.” In <i>Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference On</i>, 5053–57, 2015. <a href=\"https://doi.org/10.1109/ICASSP.2015.7178933\">https://doi.org/10.1109/ICASSP.2015.7178933</a>.","ieee":"J. Heymann, R. Haeb-Umbach, P. Golik, and R. Schlueter, “Unsupervised adaptation of a denoising autoencoder by Bayesian Feature Enhancement for reverberant asr under mismatch conditions,” in <i>Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on</i>, 2015, pp. 5053–5057."},"page":"5053-5057","keyword":["codecs","signal denoising","speech recognition","Bayesian feature enhancement","denoising autoencoder","reverberant ASR","single-channel speech recognition","speaker to microphone distances","unsupervised adaptation","Adaptation models","Noise reduction","Reverberation","Speech","Speech recognition","Training","deep neuronal networks","denoising autoencoder","feature enhancement","robust speech recognition"],"language":[{"iso":"eng"}],"_id":"11813","user_id":"44006","department":[{"_id":"54"}],"abstract":[{"text":"The parametric Bayesian Feature Enhancement (BFE) and a datadriven Denoising Autoencoder (DA) both bring performance gains in severe single-channel speech recognition conditions. The first can be adjusted to different conditions by an appropriate parameter setting, while the latter needs to be trained on conditions similar to the ones expected at decoding time, making it vulnerable to a mismatch between training and test conditions. We use a DNN backend and study reverberant ASR under three types of mismatch conditions: different room reverberation times, different speaker to microphone distances and the difference between artificially reverberated data and the recordings in a reverberant environment. We show that for these mismatch conditions BFE can provide the targets for a DA. This unsupervised adaptation provides a performance gain over the direct use of BFE and even enables to compensate for the mismatch of real and simulated reverberant data.","lang":"eng"}],"status":"public","type":"conference","publication":"Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on"},{"_id":"11861","department":[{"_id":"54"}],"user_id":"44006","keyword":["computational complexity","reverberation","speech recognition","automatic speech recognition","background noise","clean speech","computational complexity","energy compensation","logarithmic mel power spectral domain","mel frequency cepstral coefficients","microphone input signals","model-based feature compensation schemes","noisy reverberant speech automatic recognition","noisy reverberant speech features","reverberation","Atmospheric modeling","Computational modeling","Noise","Noise measurement","Reverberation","Speech","Vectors","Model-based feature compensation","observation model for reverberant and noisy speech","recursive observation model","robust automatic speech recognition"],"language":[{"iso":"eng"}],"publication":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","type":"journal_article","abstract":[{"text":"In this contribution we present a theoretical and experimental investigation into the effects of reverberation and noise on features in the logarithmic mel power spectral domain, an intermediate stage in the computation of the mel frequency cepstral coefficients, prevalent in automatic speech recognition (ASR). Gaining insight into the complex interaction between clean speech, noise, and noisy reverberant speech features is essential for any ASR system to be robust against noise and reverberation present in distant microphone input signals. The findings are gathered in a probabilistic formulation of an observation model which may be used in model-based feature compensation schemes. The proposed observation model extends previous models in three major directions: First, the contribution of additive background noise to the observation error is explicitly taken into account. Second, an energy compensation constant is introduced which ensures an unbiased estimate of the reverberant speech features, and, third, a recursive variant of the observation model is developed resulting in reduced computational complexity when used in model-based feature compensation. The experimental section is used to evaluate the accuracy of the model and to describe how its parameters can be determined from test data.","lang":"eng"}],"status":"public","date_updated":"2022-01-06T06:51:11Z","volume":22,"author":[{"first_name":"Volker","full_name":"Leutnant, Volker","last_name":"Leutnant"},{"full_name":"Krueger, Alexander","last_name":"Krueger","first_name":"Alexander"},{"first_name":"Reinhold","id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach"}],"date_created":"2019-07-12T05:29:41Z","title":"A New Observation Model in the Logarithmic Mel Power Spectral Domain for the Automatic Recognition of Noisy Reverberant Speech","doi":"10.1109/TASLP.2013.2285480","publication_identifier":{"issn":["2329-9290"]},"issue":"1","year":"2014","intvolume":"        22","page":"95-109","citation":{"bibtex":"@article{Leutnant_Krueger_Haeb-Umbach_2014, title={A New Observation Model in the Logarithmic Mel Power Spectral Domain for the Automatic Recognition of Noisy Reverberant Speech}, volume={22}, DOI={<a href=\"https://doi.org/10.1109/TASLP.2013.2285480\">10.1109/TASLP.2013.2285480</a>}, number={1}, journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing}, author={Leutnant, Volker and Krueger, Alexander and Haeb-Umbach, Reinhold}, year={2014}, pages={95–109} }","short":"V. Leutnant, A. Krueger, R. Haeb-Umbach, IEEE/ACM Transactions on Audio, Speech, and Language Processing 22 (2014) 95–109.","mla":"Leutnant, Volker, et al. “A New Observation Model in the Logarithmic Mel Power Spectral Domain for the Automatic Recognition of Noisy Reverberant Speech.” <i>IEEE/ACM Transactions on Audio, Speech, and Language Processing</i>, vol. 22, no. 1, 2014, pp. 95–109, doi:<a href=\"https://doi.org/10.1109/TASLP.2013.2285480\">10.1109/TASLP.2013.2285480</a>.","apa":"Leutnant, V., Krueger, A., &#38; Haeb-Umbach, R. (2014). A New Observation Model in the Logarithmic Mel Power Spectral Domain for the Automatic Recognition of Noisy Reverberant Speech. <i>IEEE/ACM Transactions on Audio, Speech, and Language Processing</i>, <i>22</i>(1), 95–109. <a href=\"https://doi.org/10.1109/TASLP.2013.2285480\">https://doi.org/10.1109/TASLP.2013.2285480</a>","chicago":"Leutnant, Volker, Alexander Krueger, and Reinhold Haeb-Umbach. “A New Observation Model in the Logarithmic Mel Power Spectral Domain for the Automatic Recognition of Noisy Reverberant Speech.” <i>IEEE/ACM Transactions on Audio, Speech, and Language Processing</i> 22, no. 1 (2014): 95–109. <a href=\"https://doi.org/10.1109/TASLP.2013.2285480\">https://doi.org/10.1109/TASLP.2013.2285480</a>.","ieee":"V. Leutnant, A. Krueger, and R. Haeb-Umbach, “A New Observation Model in the Logarithmic Mel Power Spectral Domain for the Automatic Recognition of Noisy Reverberant Speech,” <i>IEEE/ACM Transactions on Audio, Speech, and Language Processing</i>, vol. 22, no. 1, pp. 95–109, 2014.","ama":"Leutnant V, Krueger A, Haeb-Umbach R. A New Observation Model in the Logarithmic Mel Power Spectral Domain for the Automatic Recognition of Noisy Reverberant Speech. <i>IEEE/ACM Transactions on Audio, Speech, and Language Processing</i>. 2014;22(1):95-109. doi:<a href=\"https://doi.org/10.1109/TASLP.2013.2285480\">10.1109/TASLP.2013.2285480</a>"}},{"year":"2014","citation":{"ama":"Li J, Deng L, Gong Y, Haeb-Umbach R. An Overview of Noise-Robust Automatic Speech Recognition. <i>IEEE Transactions on Audio, Speech and Language Processing</i>. 2014;22(4):745-777. doi:<a href=\"https://doi.org/10.1109/TASLP.2014.2304637\">10.1109/TASLP.2014.2304637</a>","ieee":"J. Li, L. Deng, Y. Gong, and R. Haeb-Umbach, “An Overview of Noise-Robust Automatic Speech Recognition,” <i>IEEE Transactions on Audio, Speech and Language Processing</i>, vol. 22, no. 4, pp. 745–777, 2014.","chicago":"Li, Jinyu, Li Deng, Yifan Gong, and Reinhold Haeb-Umbach. “An Overview of Noise-Robust Automatic Speech Recognition.” <i>IEEE Transactions on Audio, Speech and Language Processing</i> 22, no. 4 (2014): 745–77. <a href=\"https://doi.org/10.1109/TASLP.2014.2304637\">https://doi.org/10.1109/TASLP.2014.2304637</a>.","bibtex":"@article{Li_Deng_Gong_Haeb-Umbach_2014, title={An Overview of Noise-Robust Automatic Speech Recognition}, volume={22}, DOI={<a href=\"https://doi.org/10.1109/TASLP.2014.2304637\">10.1109/TASLP.2014.2304637</a>}, number={4}, journal={IEEE Transactions on Audio, Speech and Language Processing}, author={Li, Jinyu and Deng, Li and Gong, Yifan and Haeb-Umbach, Reinhold}, year={2014}, pages={745–777} }","mla":"Li, Jinyu, et al. “An Overview of Noise-Robust Automatic Speech Recognition.” <i>IEEE Transactions on Audio, Speech and Language Processing</i>, vol. 22, no. 4, 2014, pp. 745–77, doi:<a href=\"https://doi.org/10.1109/TASLP.2014.2304637\">10.1109/TASLP.2014.2304637</a>.","short":"J. Li, L. Deng, Y. Gong, R. Haeb-Umbach, IEEE Transactions on Audio, Speech and Language Processing 22 (2014) 745–777.","apa":"Li, J., Deng, L., Gong, Y., &#38; Haeb-Umbach, R. (2014). An Overview of Noise-Robust Automatic Speech Recognition. <i>IEEE Transactions on Audio, Speech and Language Processing</i>, <i>22</i>(4), 745–777. <a href=\"https://doi.org/10.1109/TASLP.2014.2304637\">https://doi.org/10.1109/TASLP.2014.2304637</a>"},"page":"745-777","intvolume":"        22","issue":"4","title":"An Overview of Noise-Robust Automatic Speech Recognition","main_file_link":[{"open_access":"1","url":"http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6732927"}],"doi":"10.1109/TASLP.2014.2304637","oa":"1","date_updated":"2022-01-06T06:51:11Z","date_created":"2019-07-12T05:29:47Z","author":[{"first_name":"Jinyu","last_name":"Li","full_name":"Li, Jinyu"},{"first_name":"Li","last_name":"Deng","full_name":"Deng, Li"},{"first_name":"Yifan","last_name":"Gong","full_name":"Gong, Yifan"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold"}],"volume":22,"abstract":[{"text":"New waves of consumer-centric applications, such as voice search and voice interaction with mobile devices and home entertainment systems, increasingly require automatic speech recognition (ASR) to be robust to the full range of real-world noise and other acoustic distorting conditions. Despite its practical importance, however, the inherent links between and distinctions among the myriad of methods for noise-robust ASR have yet to be carefully studied in order to advance the field further. To this end, it is critical to establish a solid, consistent, and common mathematical foundation for noise-robust ASR, which is lacking at present. This article is intended to fill this gap and to provide a thorough overview of modern noise-robust techniques for ASR developed over the past 30 years. We emphasize methods that are proven to be successful and that are likely to sustain or expand their future applicability. We distill key insights from our comprehensive overview in this field and take a fresh look at a few old problems, which nevertheless are still highly relevant today. Specifically, we have analyzed and categorized a wide range of noise-robust techniques using five different criteria: 1) feature-domain vs. model-domain processing, 2) the use of prior knowledge about the acoustic environment distortion, 3) the use of explicit environment-distortion models, 4) deterministic vs. uncertainty processing, and 5) the use of acoustic models trained jointly with the same feature enhancement or model adaptation process used in the testing stage. With this taxonomy-oriented review, we equip the reader with the insight to choose among techniques and with the awareness of the performance-complexity tradeoffs. The pros and cons of using different noise-robust ASR techniques in practical application scenarios are provided as a guide to interested practitioners. The current challenges and future research directions in this field is also carefully analyzed.","lang":"eng"}],"status":"public","type":"journal_article","publication":"IEEE Transactions on Audio, Speech and Language Processing","keyword":["Speech recognition","compensation","distortion modeling","joint model training","noise","robustness","uncertainty processing"],"language":[{"iso":"eng"}],"_id":"11867","user_id":"44006","department":[{"_id":"54"}]},{"doi":"10.1109/ICASSP.2013.6638984","title":"GMM-based significance decoding","author":[{"first_name":"Ahmed H.","last_name":"Abdelaziz","full_name":"Abdelaziz, Ahmed H."},{"first_name":"Steffen","full_name":"Zeiler, Steffen","last_name":"Zeiler"},{"first_name":"Dorothea","full_name":"Kolossa, Dorothea","last_name":"Kolossa"},{"first_name":"Volker","last_name":"Leutnant","full_name":"Leutnant, Volker"},{"full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"date_created":"2019-07-12T05:26:53Z","date_updated":"2022-01-06T06:51:07Z","citation":{"short":"A.H. Abdelaziz, S. Zeiler, D. Kolossa, V. Leutnant, R. Haeb-Umbach, in: Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference On, 2013, pp. 6827–6831.","bibtex":"@inproceedings{Abdelaziz_Zeiler_Kolossa_Leutnant_Haeb-Umbach_2013, title={GMM-based significance decoding}, DOI={<a href=\"https://doi.org/10.1109/ICASSP.2013.6638984\">10.1109/ICASSP.2013.6638984</a>}, booktitle={Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on}, author={Abdelaziz, Ahmed H. and Zeiler, Steffen and Kolossa, Dorothea and Leutnant, Volker and Haeb-Umbach, Reinhold}, year={2013}, pages={6827–6831} }","mla":"Abdelaziz, Ahmed H., et al. “GMM-Based Significance Decoding.” <i>Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference On</i>, 2013, pp. 6827–31, doi:<a href=\"https://doi.org/10.1109/ICASSP.2013.6638984\">10.1109/ICASSP.2013.6638984</a>.","apa":"Abdelaziz, A. H., Zeiler, S., Kolossa, D., Leutnant, V., &#38; Haeb-Umbach, R. (2013). GMM-based significance decoding. In <i>Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on</i> (pp. 6827–6831). <a href=\"https://doi.org/10.1109/ICASSP.2013.6638984\">https://doi.org/10.1109/ICASSP.2013.6638984</a>","ama":"Abdelaziz AH, Zeiler S, Kolossa D, Leutnant V, Haeb-Umbach R. GMM-based significance decoding. In: <i>Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference On</i>. ; 2013:6827-6831. doi:<a href=\"https://doi.org/10.1109/ICASSP.2013.6638984\">10.1109/ICASSP.2013.6638984</a>","ieee":"A. H. Abdelaziz, S. Zeiler, D. Kolossa, V. Leutnant, and R. Haeb-Umbach, “GMM-based significance decoding,” in <i>Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on</i>, 2013, pp. 6827–6831.","chicago":"Abdelaziz, Ahmed H., Steffen Zeiler, Dorothea Kolossa, Volker Leutnant, and Reinhold Haeb-Umbach. “GMM-Based Significance Decoding.” In <i>Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference On</i>, 6827–31, 2013. <a href=\"https://doi.org/10.1109/ICASSP.2013.6638984\">https://doi.org/10.1109/ICASSP.2013.6638984</a>."},"page":"6827-6831","year":"2013","publication_identifier":{"issn":["1520-6149"]},"language":[{"iso":"eng"}],"keyword":["Bayes methods","Gaussian processes","convolution","decision theory","decoding","noise","reverberation","speech coding","speech recognition","Bayesian decision rule","GMM","Gaussian mixture models","additive noise scenarios","automatic speech recognition systems","convolutive noise scenarios","decoding approach","mathematical framework","reverberant environments","significance decoding","speech feature estimation","uncertainty-of-observation techniques","Hidden Markov models","Maximum likelihood decoding","Noise","Speech","Speech recognition","Uncertainty","Uncertainty-of-observation","modified imputation","noise robust speech recognition","significance decoding","uncertainty decoding"],"user_id":"44006","department":[{"_id":"54"}],"_id":"11716","status":"public","abstract":[{"text":"The accuracy of automatic speech recognition systems in noisy and reverberant environments can be improved notably by exploiting the uncertainty of the estimated speech features using so-called uncertainty-of-observation techniques. In this paper, we introduce a new Bayesian decision rule that can serve as a mathematical framework from which both known and new uncertainty-of-observation techniques can be either derived or approximated. The new decision rule in its direct form leads to the new significance decoding approach for Gaussian mixture models, which results in better performance compared to standard uncertainty-of-observation techniques in different additive and convolutive noise scenarios.","lang":"eng"}],"type":"conference","publication":"Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on"},{"date_updated":"2022-01-06T06:51:08Z","oa":"1","date_created":"2019-07-12T05:27:20Z","author":[{"first_name":"Aleksej","full_name":"Chinaev, Aleksej","last_name":"Chinaev"},{"last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242","first_name":"Reinhold"}],"title":"MAP-based Estimation of the Parameters of a Gaussian Mixture Model in the Presence of Noisy Observations","main_file_link":[{"url":"https://groups.uni-paderborn.de/nt/pubs/2013/ChHa13.pdf","open_access":"1"}],"doi":"10.1109/ICASSP.2013.6638279","publication_identifier":{"issn":["1520-6149"]},"related_material":{"link":[{"url":"https://groups.uni-paderborn.de/nt/pubs/2013/ChHa13_Poster.pdf","description":"Poster","relation":"supplementary_material"}]},"year":"2013","citation":{"mla":"Chinaev, Aleksej, and Reinhold Haeb-Umbach. “MAP-Based Estimation of the Parameters of a Gaussian Mixture Model in the Presence of Noisy Observations.” <i>38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013)</i>, 2013, pp. 3352–56, doi:<a href=\"https://doi.org/10.1109/ICASSP.2013.6638279\">10.1109/ICASSP.2013.6638279</a>.","bibtex":"@inproceedings{Chinaev_Haeb-Umbach_2013, title={MAP-based Estimation of the Parameters of a Gaussian Mixture Model in the Presence of Noisy Observations}, DOI={<a href=\"https://doi.org/10.1109/ICASSP.2013.6638279\">10.1109/ICASSP.2013.6638279</a>}, booktitle={38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013)}, author={Chinaev, Aleksej and Haeb-Umbach, Reinhold}, year={2013}, pages={3352–3356} }","short":"A. Chinaev, R. Haeb-Umbach, in: 38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013), 2013, pp. 3352–3356.","apa":"Chinaev, A., &#38; Haeb-Umbach, R. (2013). MAP-based Estimation of the Parameters of a Gaussian Mixture Model in the Presence of Noisy Observations. In <i>38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013)</i> (pp. 3352–3356). <a href=\"https://doi.org/10.1109/ICASSP.2013.6638279\">https://doi.org/10.1109/ICASSP.2013.6638279</a>","ama":"Chinaev A, Haeb-Umbach R. MAP-based Estimation of the Parameters of a Gaussian Mixture Model in the Presence of Noisy Observations. In: <i>38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013)</i>. ; 2013:3352-3356. doi:<a href=\"https://doi.org/10.1109/ICASSP.2013.6638279\">10.1109/ICASSP.2013.6638279</a>","ieee":"A. Chinaev and R. Haeb-Umbach, “MAP-based Estimation of the Parameters of a Gaussian Mixture Model in the Presence of Noisy Observations,” in <i>38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013)</i>, 2013, pp. 3352–3356.","chicago":"Chinaev, Aleksej, and Reinhold Haeb-Umbach. “MAP-Based Estimation of the Parameters of a Gaussian Mixture Model in the Presence of Noisy Observations.” In <i>38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013)</i>, 3352–56, 2013. <a href=\"https://doi.org/10.1109/ICASSP.2013.6638279\">https://doi.org/10.1109/ICASSP.2013.6638279</a>."},"page":"3352-3356","_id":"11740","user_id":"44006","department":[{"_id":"54"}],"keyword":["Gaussian noise","maximum likelihood estimation","parameter estimation","GMM parameter","Gaussian mixture model","MAP estimation","Map-based estimation","maximum a-posteriori estimation","maximum likelihood technique","noisy observation","sequential estimation framework","white Gaussian noise","Additive noise","Gaussian mixture model","Maximum likelihood estimation","Noise measurement","Gaussian mixture model","Maximum a posteriori estimation","Maximum likelihood estimation"],"language":[{"iso":"eng"}],"type":"conference","publication":"38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013)","abstract":[{"lang":"eng","text":"In this contribution we derive the Maximum A-Posteriori (MAP) estimates of the parameters of a Gaussian Mixture Model (GMM) in the presence of noisy observations. We assume the distortion to be white Gaussian noise of known mean and variance. An approximate conjugate prior of the GMM parameters is derived allowing for a computationally efficient implementation in a sequential estimation framework. Simulations on artificially generated data demonstrate the superiority of the proposed method compared to the Maximum Likelihood technique and to the ordinary MAP approach, whose estimates are corrected by the known statistics of the distortion in a straightforward manner."}],"status":"public"},{"volume":21,"author":[{"full_name":"Leutnant, Volker","last_name":"Leutnant","first_name":"Volker"},{"first_name":"Alexander","full_name":"Krueger, Alexander","last_name":"Krueger"},{"first_name":"Reinhold","id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach"}],"date_created":"2019-07-12T05:29:42Z","date_updated":"2022-01-06T06:51:11Z","doi":"10.1109/TASL.2013.2258013","title":"Bayesian Feature Enhancement for Reverberation and Noise Robust Speech Recognition","issue":"8","intvolume":"        21","page":"1640-1652","citation":{"ama":"Leutnant V, Krueger A, Haeb-Umbach R. Bayesian Feature Enhancement for Reverberation and Noise Robust Speech Recognition. <i>IEEE Transactions on Audio, Speech, and Language Processing</i>. 2013;21(8):1640-1652. doi:<a href=\"https://doi.org/10.1109/TASL.2013.2258013\">10.1109/TASL.2013.2258013</a>","ieee":"V. Leutnant, A. Krueger, and R. Haeb-Umbach, “Bayesian Feature Enhancement for Reverberation and Noise Robust Speech Recognition,” <i>IEEE Transactions on Audio, Speech, and Language Processing</i>, vol. 21, no. 8, pp. 1640–1652, 2013.","chicago":"Leutnant, Volker, Alexander Krueger, and Reinhold Haeb-Umbach. “Bayesian Feature Enhancement for Reverberation and Noise Robust Speech Recognition.” <i>IEEE Transactions on Audio, Speech, and Language Processing</i> 21, no. 8 (2013): 1640–52. <a href=\"https://doi.org/10.1109/TASL.2013.2258013\">https://doi.org/10.1109/TASL.2013.2258013</a>.","apa":"Leutnant, V., Krueger, A., &#38; Haeb-Umbach, R. (2013). Bayesian Feature Enhancement for Reverberation and Noise Robust Speech Recognition. <i>IEEE Transactions on Audio, Speech, and Language Processing</i>, <i>21</i>(8), 1640–1652. <a href=\"https://doi.org/10.1109/TASL.2013.2258013\">https://doi.org/10.1109/TASL.2013.2258013</a>","mla":"Leutnant, Volker, et al. “Bayesian Feature Enhancement for Reverberation and Noise Robust Speech Recognition.” <i>IEEE Transactions on Audio, Speech, and Language Processing</i>, vol. 21, no. 8, 2013, pp. 1640–52, doi:<a href=\"https://doi.org/10.1109/TASL.2013.2258013\">10.1109/TASL.2013.2258013</a>.","bibtex":"@article{Leutnant_Krueger_Haeb-Umbach_2013, title={Bayesian Feature Enhancement for Reverberation and Noise Robust Speech Recognition}, volume={21}, DOI={<a href=\"https://doi.org/10.1109/TASL.2013.2258013\">10.1109/TASL.2013.2258013</a>}, number={8}, journal={IEEE Transactions on Audio, Speech, and Language Processing}, author={Leutnant, Volker and Krueger, Alexander and Haeb-Umbach, Reinhold}, year={2013}, pages={1640–1652} }","short":"V. Leutnant, A. Krueger, R. Haeb-Umbach, IEEE Transactions on Audio, Speech, and Language Processing 21 (2013) 1640–1652."},"year":"2013","department":[{"_id":"54"}],"user_id":"44006","_id":"11862","language":[{"iso":"eng"}],"keyword":["Bayes methods","compensation","error statistics","reverberation","speech recognition","Bayesian feature enhancement","background noise","clean speech feature vectors","compensation","connected digits recognition task","error statistics","memory requirements","noisy reverberant data","posteriori probability density function","recursive formulation","reverberant logarithmic mel power spectral coefficients","robust automatic speech recognition","signal-to-noise ratios","time-variant observation","word error rate reduction","Robust automatic speech recognition","model-based Bayesian feature enhancement","observation model for reverberant and noisy speech","recursive observation model"],"publication":"IEEE Transactions on Audio, Speech, and Language Processing","type":"journal_article","status":"public","abstract":[{"text":"In this contribution we extend a previously proposed Bayesian approach for the enhancement of reverberant logarithmic mel power spectral coefficients for robust automatic speech recognition to the additional compensation of background noise. A recently proposed observation model is employed whose time-variant observation error statistics are obtained as a side product of the inference of the a posteriori probability density function of the clean speech feature vectors. Further a reduction of the computational effort and the memory requirements are achieved by using a recursive formulation of the observation model. The performance of the proposed algorithms is first experimentally studied on a connected digits recognition task with artificially created noisy reverberant data. It is shown that the use of the time-variant observation error model leads to a significant error rate reduction at low signal-to-noise ratios compared to a time-invariant model. Further experiments were conducted on a 5000 word task recorded in a reverberant and noisy environment. A significant word error rate reduction was obtained demonstrating the effectiveness of the approach on real-world data.","lang":"eng"}]},{"publication_identifier":{"issn":["1520-6149"]},"year":"2013","page":"863-867","citation":{"ama":"Vu DHT, Haeb-Umbach R. Using the turbo principle for exploiting temporal and spectral correlations in speech presence probability estimation. In: <i>38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013)</i>. ; 2013:863-867. doi:<a href=\"https://doi.org/10.1109/ICASSP.2013.6637771\">10.1109/ICASSP.2013.6637771</a>","chicago":"Vu, Dang Hai Tran, and Reinhold Haeb-Umbach. “Using the Turbo Principle for Exploiting Temporal and Spectral Correlations in Speech Presence Probability Estimation.” In <i>38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013)</i>, 863–67, 2013. <a href=\"https://doi.org/10.1109/ICASSP.2013.6637771\">https://doi.org/10.1109/ICASSP.2013.6637771</a>.","ieee":"D. H. T. Vu and R. Haeb-Umbach, “Using the turbo principle for exploiting temporal and spectral correlations in speech presence probability estimation,” in <i>38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013)</i>, 2013, pp. 863–867.","bibtex":"@inproceedings{Vu_Haeb-Umbach_2013, title={Using the turbo principle for exploiting temporal and spectral correlations in speech presence probability estimation}, DOI={<a href=\"https://doi.org/10.1109/ICASSP.2013.6637771\">10.1109/ICASSP.2013.6637771</a>}, booktitle={38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013)}, author={Vu, Dang Hai Tran and Haeb-Umbach, Reinhold}, year={2013}, pages={863–867} }","short":"D.H.T. Vu, R. Haeb-Umbach, in: 38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013), 2013, pp. 863–867.","mla":"Vu, Dang Hai Tran, and Reinhold Haeb-Umbach. “Using the Turbo Principle for Exploiting Temporal and Spectral Correlations in Speech Presence Probability Estimation.” <i>38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013)</i>, 2013, pp. 863–67, doi:<a href=\"https://doi.org/10.1109/ICASSP.2013.6637771\">10.1109/ICASSP.2013.6637771</a>.","apa":"Vu, D. H. T., &#38; Haeb-Umbach, R. (2013). Using the turbo principle for exploiting temporal and spectral correlations in speech presence probability estimation. In <i>38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013)</i> (pp. 863–867). <a href=\"https://doi.org/10.1109/ICASSP.2013.6637771\">https://doi.org/10.1109/ICASSP.2013.6637771</a>"},"date_updated":"2022-01-06T06:51:12Z","author":[{"first_name":"Dang Hai Tran","last_name":"Vu","full_name":"Vu, Dang Hai Tran"},{"full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"date_created":"2019-07-12T05:30:45Z","title":"Using the turbo principle for exploiting temporal and spectral correlations in speech presence probability estimation","doi":"10.1109/ICASSP.2013.6637771","publication":"38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013)","type":"conference","abstract":[{"lang":"eng","text":"In this paper we present a speech presence probability (SPP) estimation algorithmwhich exploits both temporal and spectral correlations of speech. To this end, the SPP estimation is formulated as the posterior probability estimation of the states of a two-dimensional (2D) Hidden Markov Model (HMM). We derive an iterative algorithm to decode the 2D-HMM which is based on the turbo principle. The experimental results show that indeed the SPP estimates improve from iteration to iteration, and further clearly outperform another state-of-the-art SPP estimation algorithm."}],"status":"public","_id":"11917","department":[{"_id":"54"}],"user_id":"44006","keyword":["correlation methods","estimation theory","hidden Markov models","iterative methods","probability","spectral analysis","speech processing","2D HMM","SPP estimates","iterative algorithm","posterior probability estimation","spectral correlation","speech presence probability estimation","state-of-the-art SPP estimation algorithm","temporal correlation","turbo principle","two-dimensional hidden Markov model","Correlation","Decoding","Estimation","Iterative decoding","Noise","Speech","Vectors"],"language":[{"iso":"eng"}]},{"language":[{"iso":"eng"}],"keyword":["MAP parameter estimation","noise power estimation","speech enhancement"],"user_id":"44006","department":[{"_id":"54"}],"_id":"11745","status":"public","abstract":[{"lang":"eng","text":"In this paper we present a novel noise power spectral density tracking algorithm and its use in single-channel speech enhancement. It has the unique feature that it is able to track the noise statistics even if speech is dominant in a given time-frequency bin. As a consequence it can follow non-stationary noise superposed by speech, even in the critical case of rising noise power. The algorithm requires an initial estimate of the power spectrum of speech and is thus meant to be used as a postprocessor to a first speech enhancement stage. An experimental comparison with a state-of-the-art noise tracking algorithm demonstrates lower estimation errors under low SNR conditions and smaller fluctuations of the estimated values, resulting in improved speech quality as measured by PESQ scores."}],"type":"conference","publication":"37th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2012)","main_file_link":[{"open_access":"1","url":"https://groups.uni-paderborn.de/nt/pubs/2012/ChKrDaHa12.pdf"}],"title":"Improved Noise Power Spectral Density Tracking by a MAP-based Postprocessor","date_created":"2019-07-12T05:27:26Z","author":[{"full_name":"Chinaev, Aleksej","last_name":"Chinaev","first_name":"Aleksej"},{"full_name":"Krueger, Alexander","last_name":"Krueger","first_name":"Alexander"},{"last_name":"Tran Vu","full_name":"Tran Vu, Dang Hai","first_name":"Dang Hai"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold"}],"date_updated":"2022-01-06T06:51:08Z","oa":"1","citation":{"chicago":"Chinaev, Aleksej, Alexander Krueger, Dang Hai Tran Vu, and Reinhold Haeb-Umbach. “Improved Noise Power Spectral Density Tracking by a MAP-Based Postprocessor.” In <i>37th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2012)</i>, 2012.","ieee":"A. Chinaev, A. Krueger, D. H. Tran Vu, and R. Haeb-Umbach, “Improved Noise Power Spectral Density Tracking by a MAP-based Postprocessor,” in <i>37th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2012)</i>, 2012.","ama":"Chinaev A, Krueger A, Tran Vu DH, Haeb-Umbach R. Improved Noise Power Spectral Density Tracking by a MAP-based Postprocessor. In: <i>37th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2012)</i>. ; 2012.","apa":"Chinaev, A., Krueger, A., Tran Vu, D. H., &#38; Haeb-Umbach, R. (2012). Improved Noise Power Spectral Density Tracking by a MAP-based Postprocessor. In <i>37th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2012)</i>.","short":"A. Chinaev, A. Krueger, D.H. Tran Vu, R. Haeb-Umbach, in: 37th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2012), 2012.","mla":"Chinaev, Aleksej, et al. “Improved Noise Power Spectral Density Tracking by a MAP-Based Postprocessor.” <i>37th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2012)</i>, 2012.","bibtex":"@inproceedings{Chinaev_Krueger_Tran Vu_Haeb-Umbach_2012, title={Improved Noise Power Spectral Density Tracking by a MAP-based Postprocessor}, booktitle={37th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2012)}, author={Chinaev, Aleksej and Krueger, Alexander and Tran Vu, Dang Hai and Haeb-Umbach, Reinhold}, year={2012} }"},"year":"2012","related_material":{"link":[{"url":"https://groups.uni-paderborn.de/nt/pubs/2012/ChKrDaHa12_Talk.pdf","relation":"supplementary_material","description":"Presentation"}]}},{"keyword":["acoustical transfer function ratio","adaptive eigenvector tracking","array signal processing","beamformer design","blocking matrix","eigenvalues and eigenfunctions","eigenvector-based transfer function ratios estimation","generalized sidelobe canceler","interference reduction","iterative methods","power iteration method","reduced speech distortions","reverberant enclosure","reverberation","speech enhancement","stationary noise"],"language":[{"iso":"eng"}],"publication":"IEEE Transactions on Audio, Speech, and Language Processing","abstract":[{"text":"In this paper, we present a novel blocking matrix and fixed beamformer design for a generalized sidelobe canceler for speech enhancement in a reverberant enclosure. They are based on a new method for estimating the acoustical transfer function ratios in the presence of stationary noise. The estimation method relies on solving a generalized eigenvalue problem in each frequency bin. An adaptive eigenvector tracking utilizing the power iteration method is employed and shown to achieve a high convergence speed. Simulation results demonstrate that the proposed beamformer leads to better noise and interference reduction and reduced speech distortions compared to other blocking matrix designs from the literature.","lang":"eng"}],"date_created":"2019-07-12T05:29:28Z","title":"Speech Enhancement With a GSC-Like Structure Employing Eigenvector-Based Transfer Function Ratios Estimation","issue":"1","year":"2011","_id":"11850","department":[{"_id":"54"}],"user_id":"44006","type":"journal_article","status":"public","oa":"1","date_updated":"2022-01-06T06:51:11Z","volume":19,"author":[{"first_name":"Alexander","full_name":"Krueger, Alexander","last_name":"Krueger"},{"full_name":"Warsitz, Ernst","last_name":"Warsitz","first_name":"Ernst"},{"first_name":"Reinhold","full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach"}],"doi":"10.1109/TASL.2010.2047324","main_file_link":[{"open_access":"1","url":"https://groups.uni-paderborn.de/nt/pubs/2011/KrWaHa11.pdf"}],"page":"206-219","intvolume":"        19","citation":{"ama":"Krueger A, Warsitz E, Haeb-Umbach R. Speech Enhancement With a GSC-Like Structure Employing Eigenvector-Based Transfer Function Ratios Estimation. <i>IEEE Transactions on Audio, Speech, and Language Processing</i>. 2011;19(1):206-219. doi:<a href=\"https://doi.org/10.1109/TASL.2010.2047324\">10.1109/TASL.2010.2047324</a>","ieee":"A. Krueger, E. Warsitz, and R. Haeb-Umbach, “Speech Enhancement With a GSC-Like Structure Employing Eigenvector-Based Transfer Function Ratios Estimation,” <i>IEEE Transactions on Audio, Speech, and Language Processing</i>, vol. 19, no. 1, pp. 206–219, 2011.","chicago":"Krueger, Alexander, Ernst Warsitz, and Reinhold Haeb-Umbach. “Speech Enhancement With a GSC-Like Structure Employing Eigenvector-Based Transfer Function Ratios Estimation.” <i>IEEE Transactions on Audio, Speech, and Language Processing</i> 19, no. 1 (2011): 206–19. <a href=\"https://doi.org/10.1109/TASL.2010.2047324\">https://doi.org/10.1109/TASL.2010.2047324</a>.","short":"A. Krueger, E. Warsitz, R. Haeb-Umbach, IEEE Transactions on Audio, Speech, and Language Processing 19 (2011) 206–219.","bibtex":"@article{Krueger_Warsitz_Haeb-Umbach_2011, title={Speech Enhancement With a GSC-Like Structure Employing Eigenvector-Based Transfer Function Ratios Estimation}, volume={19}, DOI={<a href=\"https://doi.org/10.1109/TASL.2010.2047324\">10.1109/TASL.2010.2047324</a>}, number={1}, journal={IEEE Transactions on Audio, Speech, and Language Processing}, author={Krueger, Alexander and Warsitz, Ernst and Haeb-Umbach, Reinhold}, year={2011}, pages={206–219} }","mla":"Krueger, Alexander, et al. “Speech Enhancement With a GSC-Like Structure Employing Eigenvector-Based Transfer Function Ratios Estimation.” <i>IEEE Transactions on Audio, Speech, and Language Processing</i>, vol. 19, no. 1, 2011, pp. 206–19, doi:<a href=\"https://doi.org/10.1109/TASL.2010.2047324\">10.1109/TASL.2010.2047324</a>.","apa":"Krueger, A., Warsitz, E., &#38; Haeb-Umbach, R. (2011). Speech Enhancement With a GSC-Like Structure Employing Eigenvector-Based Transfer Function Ratios Estimation. <i>IEEE Transactions on Audio, Speech, and Language Processing</i>, <i>19</i>(1), 206–219. <a href=\"https://doi.org/10.1109/TASL.2010.2047324\">https://doi.org/10.1109/TASL.2010.2047324</a>"}},{"year":"2010","citation":{"ama":"Tran Vu DH, Haeb-Umbach R. Blind speech separation employing directional statistics in an Expectation Maximization framework. In: <i>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2010)</i>. ; 2010:241-244. doi:<a href=\"https://doi.org/10.1109/ICASSP.2010.5495994\">10.1109/ICASSP.2010.5495994</a>","chicago":"Tran Vu, Dang Hai, and Reinhold Haeb-Umbach. “Blind Speech Separation Employing Directional Statistics in an Expectation Maximization Framework.” In <i>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2010)</i>, 241–44, 2010. <a href=\"https://doi.org/10.1109/ICASSP.2010.5495994\">https://doi.org/10.1109/ICASSP.2010.5495994</a>.","ieee":"D. H. Tran Vu and R. Haeb-Umbach, “Blind speech separation employing directional statistics in an Expectation Maximization framework,” in <i>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2010)</i>, 2010, pp. 241–244.","bibtex":"@inproceedings{Tran Vu_Haeb-Umbach_2010, title={Blind speech separation employing directional statistics in an Expectation Maximization framework}, DOI={<a href=\"https://doi.org/10.1109/ICASSP.2010.5495994\">10.1109/ICASSP.2010.5495994</a>}, booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2010)}, author={Tran Vu, Dang Hai and Haeb-Umbach, Reinhold}, year={2010}, pages={241–244} }","short":"D.H. Tran Vu, R. Haeb-Umbach, in: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2010), 2010, pp. 241–244.","mla":"Tran Vu, Dang Hai, and Reinhold Haeb-Umbach. “Blind Speech Separation Employing Directional Statistics in an Expectation Maximization Framework.” <i>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2010)</i>, 2010, pp. 241–44, doi:<a href=\"https://doi.org/10.1109/ICASSP.2010.5495994\">10.1109/ICASSP.2010.5495994</a>.","apa":"Tran Vu, D. H., &#38; Haeb-Umbach, R. (2010). Blind speech separation employing directional statistics in an Expectation Maximization framework. In <i>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2010)</i> (pp. 241–244). <a href=\"https://doi.org/10.1109/ICASSP.2010.5495994\">https://doi.org/10.1109/ICASSP.2010.5495994</a>"},"page":"241-244","title":"Blind speech separation employing directional statistics in an Expectation Maximization framework","main_file_link":[{"url":"https://groups.uni-paderborn.de/nt/pubs/2010/DaHa10-2.pdf","open_access":"1"}],"doi":"10.1109/ICASSP.2010.5495994","date_updated":"2022-01-06T06:51:12Z","oa":"1","date_created":"2019-07-12T05:30:40Z","author":[{"last_name":"Tran Vu","full_name":"Tran Vu, Dang Hai","first_name":"Dang Hai"},{"full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"abstract":[{"lang":"eng","text":"In this paper we propose to employ directional statistics in a complex vector space to approach the problem of blind speech separation in the presence of spatially correlated noise. We interpret the values of the short time Fourier transform of the microphone signals to be draws from a mixture of complex Watson distributions, a probabilistic model which naturally accounts for spatial aliasing. The parameters of the density are related to the a priori source probabilities, the power of the sources and the transfer function ratios from sources to sensors. Estimation formulas are derived for these parameters by employing the Expectation Maximization (EM) algorithm. The E-step corresponds to the estimation of the source presence probabilities for each time-frequency bin, while the M-step leads to a maximum signal-to-noise ratio (MaxSNR) beamformer in the presence of uncertainty about the source activity. Experimental results are reported for an implementation in a generalized sidelobe canceller (GSC) like spatial beamforming configuration for 3 speech sources with significant coherent noise in reverberant environments, demonstrating the usefulness of the novel modeling framework."}],"status":"public","type":"conference","publication":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2010)","keyword":["array signal processing","blind source separation","blind speech separation","complex vector space","complex Watson distribution","directional statistics","expectation-maximisation algorithm","expectation maximization algorithm","Fourier transform","Fourier transforms","generalized sidelobe canceller","interference suppression","maximum signal-to-noise ratio beamformer","microphone signal","probabilistic model","spatial aliasing","spatial beamforming configuration","speech enhancement","statistical distributions"],"language":[{"iso":"eng"}],"_id":"11913","user_id":"44006","department":[{"_id":"54"}]},{"oa":"1","date_updated":"2022-01-06T06:51:07Z","author":[{"first_name":"Maik","last_name":"Bevermeier","full_name":"Bevermeier, Maik"},{"last_name":"Peschke","full_name":"Peschke, Sven","first_name":"Sven"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"date_created":"2019-07-12T05:27:01Z","title":"Robust vehicle localization based on multi-level sensor fusion and online parameter estimation","main_file_link":[{"open_access":"1","url":"https://groups.uni-paderborn.de/nt/pubs/2009/BePeHa09.pdf"}],"doi":"10.1109/WPNC.2009.4907833","year":"2009","citation":{"apa":"Bevermeier, M., Peschke, S., &#38; Haeb-Umbach, R. (2009). Robust vehicle localization based on multi-level sensor fusion and online parameter estimation. In <i>6th Workshop on Positioning Navigation and Communication (WPNC 2009)</i> (pp. 235–242). <a href=\"https://doi.org/10.1109/WPNC.2009.4907833\">https://doi.org/10.1109/WPNC.2009.4907833</a>","bibtex":"@inproceedings{Bevermeier_Peschke_Haeb-Umbach_2009, title={Robust vehicle localization based on multi-level sensor fusion and online parameter estimation}, DOI={<a href=\"https://doi.org/10.1109/WPNC.2009.4907833\">10.1109/WPNC.2009.4907833</a>}, booktitle={6th Workshop on Positioning Navigation and Communication (WPNC 2009)}, author={Bevermeier, Maik and Peschke, Sven and Haeb-Umbach, Reinhold}, year={2009}, pages={235–242} }","mla":"Bevermeier, Maik, et al. “Robust Vehicle Localization Based on Multi-Level Sensor Fusion and Online Parameter Estimation.” <i>6th Workshop on Positioning Navigation and Communication (WPNC 2009)</i>, 2009, pp. 235–42, doi:<a href=\"https://doi.org/10.1109/WPNC.2009.4907833\">10.1109/WPNC.2009.4907833</a>.","short":"M. Bevermeier, S. Peschke, R. Haeb-Umbach, in: 6th Workshop on Positioning Navigation and Communication (WPNC 2009), 2009, pp. 235–242.","ama":"Bevermeier M, Peschke S, Haeb-Umbach R. Robust vehicle localization based on multi-level sensor fusion and online parameter estimation. In: <i>6th Workshop on Positioning Navigation and Communication (WPNC 2009)</i>. ; 2009:235-242. doi:<a href=\"https://doi.org/10.1109/WPNC.2009.4907833\">10.1109/WPNC.2009.4907833</a>","ieee":"M. Bevermeier, S. Peschke, and R. Haeb-Umbach, “Robust vehicle localization based on multi-level sensor fusion and online parameter estimation,” in <i>6th Workshop on Positioning Navigation and Communication (WPNC 2009)</i>, 2009, pp. 235–242.","chicago":"Bevermeier, Maik, Sven Peschke, and Reinhold Haeb-Umbach. “Robust Vehicle Localization Based on Multi-Level Sensor Fusion and Online Parameter Estimation.” In <i>6th Workshop on Positioning Navigation and Communication (WPNC 2009)</i>, 235–42, 2009. <a href=\"https://doi.org/10.1109/WPNC.2009.4907833\">https://doi.org/10.1109/WPNC.2009.4907833</a>."},"page":"235-242","_id":"11723","user_id":"44006","department":[{"_id":"54"}],"keyword":["covariance matrices","expectation-maximisation algorithm","expectation-maximization algorithm","global positioning system","Global Positioning System","GPS","inertial measurement unit","interacting multiple model approach","Kalman filters","multilevel sensor fusion","narrow street canyons","narrow tunnels","online parameter estimation","parameter estimation","road vehicles","robust vehicle localization","sensor fusion","state noise covariances","time-variant multilevel Kalman filter","vehicle tracking algorithm"],"language":[{"iso":"eng"}],"type":"conference","publication":"6th Workshop on Positioning Navigation and Communication (WPNC 2009)","abstract":[{"lang":"eng","text":"In this paper we present a novel vehicle tracking algorithm, which is based on multi-level sensor fusion of GPS (global positioning system) with Inertial Measurement Unit sensor data. It is shown that the robustness of the system to temporary dropouts of the GPS signal, which may occur due to limited visibility of satellites in narrow street canyons or tunnels, is greatly improved by sensor fusion. We further demonstrate how the observation and state noise covariances of the employed Kalman filters can be estimated alongside the filtering by an application of the Expectation-Maximization algorithm. The proposed time-variant multi-level Kalman filter is shown to outperform an Interacting Multiple Model approach while at the same time being computationally less demanding."}],"status":"public"},{"issue":"8","citation":{"ama":"Windmann S, Haeb-Umbach R. Parameter Estimation of a State-Space Model of Noise for Robust Speech Recognition. <i>IEEE Transactions on Audio, Speech, and Language Processing</i>. 2009;17(8):1577-1590. doi:<a href=\"https://doi.org/10.1109/TASL.2009.2023172\">10.1109/TASL.2009.2023172</a>","ieee":"S. Windmann and R. Haeb-Umbach, “Parameter Estimation of a State-Space Model of Noise for Robust Speech Recognition,” <i>IEEE Transactions on Audio, Speech, and Language Processing</i>, vol. 17, no. 8, pp. 1577–1590, 2009.","chicago":"Windmann, Stefan, and Reinhold Haeb-Umbach. “Parameter Estimation of a State-Space Model of Noise for Robust Speech Recognition.” <i>IEEE Transactions on Audio, Speech, and Language Processing</i> 17, no. 8 (2009): 1577–90. <a href=\"https://doi.org/10.1109/TASL.2009.2023172\">https://doi.org/10.1109/TASL.2009.2023172</a>.","apa":"Windmann, S., &#38; Haeb-Umbach, R. (2009). Parameter Estimation of a State-Space Model of Noise for Robust Speech Recognition. <i>IEEE Transactions on Audio, Speech, and Language Processing</i>, <i>17</i>(8), 1577–1590. <a href=\"https://doi.org/10.1109/TASL.2009.2023172\">https://doi.org/10.1109/TASL.2009.2023172</a>","short":"S. Windmann, R. Haeb-Umbach, IEEE Transactions on Audio, Speech, and Language Processing 17 (2009) 1577–1590.","bibtex":"@article{Windmann_Haeb-Umbach_2009, title={Parameter Estimation of a State-Space Model of Noise for Robust Speech Recognition}, volume={17}, DOI={<a href=\"https://doi.org/10.1109/TASL.2009.2023172\">10.1109/TASL.2009.2023172</a>}, number={8}, journal={IEEE Transactions on Audio, Speech, and Language Processing}, author={Windmann, Stefan and Haeb-Umbach, Reinhold}, year={2009}, pages={1577–1590} }","mla":"Windmann, Stefan, and Reinhold Haeb-Umbach. “Parameter Estimation of a State-Space Model of Noise for Robust Speech Recognition.” <i>IEEE Transactions on Audio, Speech, and Language Processing</i>, vol. 17, no. 8, 2009, pp. 1577–90, doi:<a href=\"https://doi.org/10.1109/TASL.2009.2023172\">10.1109/TASL.2009.2023172</a>."},"intvolume":"        17","page":"1577-1590","year":"2009","date_created":"2019-07-12T05:31:09Z","author":[{"first_name":"Stefan","last_name":"Windmann","full_name":"Windmann, Stefan"},{"last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold","first_name":"Reinhold"}],"volume":17,"oa":"1","date_updated":"2022-01-06T06:51:12Z","main_file_link":[{"open_access":"1","url":"https://groups.uni-paderborn.de/nt/pubs/2009/WiHa09-2.pdf"}],"doi":"10.1109/TASL.2009.2023172","title":"Parameter Estimation of a State-Space Model of Noise for Robust Speech Recognition","type":"journal_article","publication":"IEEE Transactions on Audio, Speech, and Language Processing","status":"public","abstract":[{"lang":"eng","text":"In this paper, parameter estimation of a state-space model of noise or noisy speech cepstra is investigated. A blockwise EM algorithm is derived for the estimation of the state and observation noise covariance from noise-only input data. It is supposed to be used during the offline training mode of a speech recognizer. Further a sequential online EM algorithm is developed to adapt the observation noise covariance on noisy speech cepstra at its input. The estimated parameters are then used in model-based speech feature enhancement for noise-robust automatic speech recognition. Experiments on the AURORA4 database lead to improved recognition results with a linear state model compared to the assumption of stationary noise."}],"user_id":"44006","department":[{"_id":"54"}],"_id":"11938","language":[{"iso":"eng"}],"keyword":["AURORA4 database","blockwise EM algorithm","covariance analysis","linear state model","noise covariance","noise-robust automatic speech recognition","noisy speech cepstra","offline training mode","parameter estimation","speech recognition","speech recognition equipment","speech recognizer","state-space methods","state-space model"]},{"year":"2008","page":"73-76","citation":{"ieee":"E. Warsitz, A. Krueger, and R. Haeb-Umbach, “Speech enhancement with a new generalized eigenvector blocking matrix for application in a generalized sidelobe canceller,” in <i>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2008)</i>, 2008, pp. 73–76.","chicago":"Warsitz, Ernst, Alexander Krueger, and Reinhold Haeb-Umbach. “Speech Enhancement with a New Generalized Eigenvector Blocking Matrix for Application in a Generalized Sidelobe Canceller.” In <i>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2008)</i>, 73–76, 2008. <a href=\"https://doi.org/10.1109/ICASSP.2008.4517549\">https://doi.org/10.1109/ICASSP.2008.4517549</a>.","ama":"Warsitz E, Krueger A, Haeb-Umbach R. Speech enhancement with a new generalized eigenvector blocking matrix for application in a generalized sidelobe canceller. In: <i>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2008)</i>. ; 2008:73-76. doi:<a href=\"https://doi.org/10.1109/ICASSP.2008.4517549\">10.1109/ICASSP.2008.4517549</a>","short":"E. Warsitz, A. Krueger, R. Haeb-Umbach, in: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2008), 2008, pp. 73–76.","bibtex":"@inproceedings{Warsitz_Krueger_Haeb-Umbach_2008, title={Speech enhancement with a new generalized eigenvector blocking matrix for application in a generalized sidelobe canceller}, DOI={<a href=\"https://doi.org/10.1109/ICASSP.2008.4517549\">10.1109/ICASSP.2008.4517549</a>}, booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2008)}, author={Warsitz, Ernst and Krueger, Alexander and Haeb-Umbach, Reinhold}, year={2008}, pages={73–76} }","mla":"Warsitz, Ernst, et al. “Speech Enhancement with a New Generalized Eigenvector Blocking Matrix for Application in a Generalized Sidelobe Canceller.” <i>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2008)</i>, 2008, pp. 73–76, doi:<a href=\"https://doi.org/10.1109/ICASSP.2008.4517549\">10.1109/ICASSP.2008.4517549</a>.","apa":"Warsitz, E., Krueger, A., &#38; Haeb-Umbach, R. (2008). Speech enhancement with a new generalized eigenvector blocking matrix for application in a generalized sidelobe canceller. In <i>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2008)</i> (pp. 73–76). <a href=\"https://doi.org/10.1109/ICASSP.2008.4517549\">https://doi.org/10.1109/ICASSP.2008.4517549</a>"},"title":"Speech enhancement with a new generalized eigenvector blocking matrix for application in a generalized sidelobe canceller","doi":"10.1109/ICASSP.2008.4517549","main_file_link":[{"url":"https://groups.uni-paderborn.de/nt/pubs/2008/WaKrHa08.pdf","open_access":"1"}],"date_updated":"2022-01-06T06:51:12Z","oa":"1","date_created":"2019-07-12T05:31:06Z","author":[{"last_name":"Warsitz","full_name":"Warsitz, Ernst","first_name":"Ernst"},{"last_name":"Krueger","full_name":"Krueger, Alexander","first_name":"Alexander"},{"first_name":"Reinhold","full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach"}],"abstract":[{"lang":"eng","text":"The generalized sidelobe canceller by Griffith and Jim is a robust beamforming method to enhance a desired (speech) signal in the presence of stationary noise. Its performance depends to a high degree on the construction of the blocking matrix which produces noise reference signals for the subsequent adaptive interference canceller. Especially in reverberated environments the beamformer may suffer from signal leakage and reduced noise suppression. In this paper a new blocking matrix is proposed. It is based on a generalized eigenvalue problem whose solution provides an indirect estimation of the transfer functions from the source to the sensors. The quality of the new generalized eigenvector blocking matrix is studied in simulated rooms with different reverberation times and is compared to alternatives proposed in the literature."}],"status":"public","publication":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2008)","type":"conference","keyword":["adaptive interference canceller","adaptive signal processing","array signal processing","beamforming method","eigenvalues and eigenfunctions","generalized eigenvector blocking matrix","generalized sidelobe canceller","interference suppression","matrix algebra","noise suppression","speech enhancement","transfer function estimation","transfer functions"],"language":[{"iso":"eng"}],"_id":"11935","department":[{"_id":"54"}],"user_id":"44006"},{"title":"Modeling the dynamics of speech and noise for speech feature enhancement in ASR","main_file_link":[{"url":"https://groups.uni-paderborn.de/nt/pubs/2008/WiHa08-1.pdf","open_access":"1"}],"doi":"10.1109/ICASSP.2008.4518633","date_updated":"2022-01-06T06:51:12Z","oa":"1","author":[{"first_name":"Stefan","last_name":"Windmann","full_name":"Windmann, Stefan"},{"last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242","first_name":"Reinhold"}],"date_created":"2019-07-12T05:31:11Z","year":"2008","citation":{"ieee":"S. Windmann and R. Haeb-Umbach, “Modeling the dynamics of speech and noise for speech feature enhancement in ASR,” in <i>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2008)</i>, 2008, pp. 4409–4412.","chicago":"Windmann, Stefan, and Reinhold Haeb-Umbach. “Modeling the Dynamics of Speech and Noise for Speech Feature Enhancement in ASR.” In <i>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2008)</i>, 4409–12, 2008. <a href=\"https://doi.org/10.1109/ICASSP.2008.4518633\">https://doi.org/10.1109/ICASSP.2008.4518633</a>.","ama":"Windmann S, Haeb-Umbach R. Modeling the dynamics of speech and noise for speech feature enhancement in ASR. In: <i>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2008)</i>. ; 2008:4409-4412. doi:<a href=\"https://doi.org/10.1109/ICASSP.2008.4518633\">10.1109/ICASSP.2008.4518633</a>","short":"S. Windmann, R. Haeb-Umbach, in: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2008), 2008, pp. 4409–4412.","mla":"Windmann, Stefan, and Reinhold Haeb-Umbach. “Modeling the Dynamics of Speech and Noise for Speech Feature Enhancement in ASR.” <i>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2008)</i>, 2008, pp. 4409–12, doi:<a href=\"https://doi.org/10.1109/ICASSP.2008.4518633\">10.1109/ICASSP.2008.4518633</a>.","bibtex":"@inproceedings{Windmann_Haeb-Umbach_2008, title={Modeling the dynamics of speech and noise for speech feature enhancement in ASR}, DOI={<a href=\"https://doi.org/10.1109/ICASSP.2008.4518633\">10.1109/ICASSP.2008.4518633</a>}, booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2008)}, author={Windmann, Stefan and Haeb-Umbach, Reinhold}, year={2008}, pages={4409–4412} }","apa":"Windmann, S., &#38; Haeb-Umbach, R. (2008). Modeling the dynamics of speech and noise for speech feature enhancement in ASR. In <i>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2008)</i> (pp. 4409–4412). <a href=\"https://doi.org/10.1109/ICASSP.2008.4518633\">https://doi.org/10.1109/ICASSP.2008.4518633</a>"},"page":"4409-4412","keyword":["a posteriori probability","AURORA2 database","Bayesian inference","Bayes methods","channel bank filters","extended Kalman filter banks","hidden noise state variable","Kalman filters","noise dynamics","speech enhancement","speech feature enhancement","speech feature trajectory","switching linear dynamical model approach"],"language":[{"iso":"eng"}],"_id":"11939","user_id":"44006","department":[{"_id":"54"}],"abstract":[{"lang":"eng","text":"In this paper a switching linear dynamical model (SLDM) approach for speech feature enhancement is improved by employing more accurate models for the dynamics of speech and noise. The model of the clean speech feature trajectory is improved by augmenting the state vector to capture information derived from the delta features. Further a hidden noise state variable is introduced to obtain a more elaborated model for the noise dynamics. Approximate Bayesian inference in the SLDM is carried out by a bank of extended Kalman filters, whose outputs are combined according to the a posteriori probability of the individual state models. Experimental results on the AURORA2 database show improved recognition accuracy."}],"status":"public","type":"conference","publication":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2008)"},{"citation":{"ama":"Peschke S, Haeb-Umbach R. Velocity Estimation of Mobile Terminals by Exploiting GSM Downlink Signalling. In: <i>4th Workshop on Positioning Navigation and Communication (WPNC 2007)</i>. ; 2007:217-222. doi:<a href=\"https://doi.org/10.1109/WPNC.2007.353637\">10.1109/WPNC.2007.353637</a>","chicago":"Peschke, Sven, and Reinhold Haeb-Umbach. “Velocity Estimation of Mobile Terminals by Exploiting GSM Downlink Signalling.” In <i>4th Workshop on Positioning Navigation and Communication (WPNC 2007)</i>, 217–22, 2007. <a href=\"https://doi.org/10.1109/WPNC.2007.353637\">https://doi.org/10.1109/WPNC.2007.353637</a>.","ieee":"S. Peschke and R. Haeb-Umbach, “Velocity Estimation of Mobile Terminals by Exploiting GSM Downlink Signalling,” in <i>4th Workshop on Positioning Navigation and Communication (WPNC 2007)</i>, 2007, pp. 217–222.","bibtex":"@inproceedings{Peschke_Haeb-Umbach_2007, title={Velocity Estimation of Mobile Terminals by Exploiting GSM Downlink Signalling}, DOI={<a href=\"https://doi.org/10.1109/WPNC.2007.353637\">10.1109/WPNC.2007.353637</a>}, booktitle={4th Workshop on Positioning Navigation and Communication (WPNC 2007)}, author={Peschke, Sven and Haeb-Umbach, Reinhold}, year={2007}, pages={217–222} }","short":"S. Peschke, R. Haeb-Umbach, in: 4th Workshop on Positioning Navigation and Communication (WPNC 2007), 2007, pp. 217–222.","mla":"Peschke, Sven, and Reinhold Haeb-Umbach. “Velocity Estimation of Mobile Terminals by Exploiting GSM Downlink Signalling.” <i>4th Workshop on Positioning Navigation and Communication (WPNC 2007)</i>, 2007, pp. 217–22, doi:<a href=\"https://doi.org/10.1109/WPNC.2007.353637\">10.1109/WPNC.2007.353637</a>.","apa":"Peschke, S., &#38; Haeb-Umbach, R. (2007). Velocity Estimation of Mobile Terminals by Exploiting GSM Downlink Signalling. In <i>4th Workshop on Positioning Navigation and Communication (WPNC 2007)</i> (pp. 217–222). <a href=\"https://doi.org/10.1109/WPNC.2007.353637\">https://doi.org/10.1109/WPNC.2007.353637</a>"},"page":"217-222","year":"2007","main_file_link":[{"open_access":"1","url":"https://groups.uni-paderborn.de/nt/pubs/2007/PeHa07.pdf"}],"doi":"10.1109/WPNC.2007.353637","title":"Velocity Estimation of Mobile Terminals by Exploiting GSM Downlink Signalling","date_created":"2019-07-12T05:30:06Z","author":[{"last_name":"Peschke","full_name":"Peschke, Sven","first_name":"Sven"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold"}],"date_updated":"2022-01-06T06:51:11Z","oa":"1","status":"public","abstract":[{"lang":"eng","text":"In this paper, we experimentally evaluate algorithms for velocity estimation of a GSM 900 mobile terminal which are based on the analysis of the statistical properties of the fast fading process. It is shown how theses statistics can be obtained from the training sequences present in downlink transmission bursts without establishing an active connection. Realistic simulations of a GSM channel according to the COST 207 channel models have been conducted. These models incorporate effects like multipath propagation, fading, cochannel interference and additive noise. It is shown that velocity estimation by searching for the maximum slope of the power density spectrum of the fast fading performs best."}],"type":"conference","publication":"4th Workshop on Positioning Navigation and Communication (WPNC 2007)","language":[{"iso":"eng"}],"keyword":["additive noise","cellular radio","channel estimation","cochannel interference","COST 207 channel models","downlink transmission bursts","fading channels","fading process","GSM downlink signalling","mobile terminals","multipath channels","multipath propagation","power density spectrum","statistical analysis","statistical properties","telecommunication links","telecommunication terminals","velocity estimation"],"user_id":"44006","department":[{"_id":"54"}],"_id":"11883"},{"keyword":["acoustic signal processing","arbitrary transfer function","array signal processing","blind acoustic beamforming","direction-of-arrival","direction-of-arrival estimation","eigenvalues and eigenfunctions","generalized eigenvalue decomposition","gradient ascent adaptation algorithm","microphone arrays","microphones","narrowband array beamforming","sensor array","single-channel post-filter","spatially colored noise","transfer functions"],"language":[{"iso":"eng"}],"abstract":[{"text":"Maximizing the output signal-to-noise ratio (SNR) of a sensor array in the presence of spatially colored noise leads to a generalized eigenvalue problem. While this approach has extensively been employed in narrowband (antenna) array beamforming, it is typically not used for broadband (microphone) array beamforming due to the uncontrolled amount of speech distortion introduced by a narrowband SNR criterion. In this paper, we show how the distortion of the desired signal can be controlled by a single-channel post-filter, resulting in a performance comparable to the generalized minimum variance distortionless response beamformer, where arbitrary transfer functions relate the source and the microphones. Results are given both for directional and diffuse noise. A novel gradient ascent adaptation algorithm is presented, and its good convergence properties are experimentally revealed by comparison with alternatives from the literature. A key feature of the proposed beamformer is that it operates blindly, i.e., it neither requires knowledge about the array geometry nor an explicit estimation of the transfer functions from source to sensors or the direction-of-arrival.","lang":"eng"}],"publication":"IEEE Transactions on Audio, Speech, and Language Processing","title":"Blind Acoustic Beamforming Based on Generalized Eigenvalue Decomposition","date_created":"2019-07-12T05:30:57Z","year":"2007","issue":"5","_id":"11927","user_id":"44006","department":[{"_id":"54"}],"status":"public","type":"journal_article","main_file_link":[{"url":"https://groups.uni-paderborn.de/nt/pubs/2007/WaHa07.pdf","open_access":"1"}],"doi":"10.1109/TASL.2007.898454","oa":"1","date_updated":"2022-01-06T06:51:12Z","author":[{"first_name":"Ernst","last_name":"Warsitz","full_name":"Warsitz, Ernst"},{"last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242","first_name":"Reinhold"}],"volume":15,"citation":{"bibtex":"@article{Warsitz_Haeb-Umbach_2007, title={Blind Acoustic Beamforming Based on Generalized Eigenvalue Decomposition}, volume={15}, DOI={<a href=\"https://doi.org/10.1109/TASL.2007.898454\">10.1109/TASL.2007.898454</a>}, number={5}, journal={IEEE Transactions on Audio, Speech, and Language Processing}, author={Warsitz, Ernst and Haeb-Umbach, Reinhold}, year={2007}, pages={1529–1539} }","mla":"Warsitz, Ernst, and Reinhold Haeb-Umbach. “Blind Acoustic Beamforming Based on Generalized Eigenvalue Decomposition.” <i>IEEE Transactions on Audio, Speech, and Language Processing</i>, vol. 15, no. 5, 2007, pp. 1529–39, doi:<a href=\"https://doi.org/10.1109/TASL.2007.898454\">10.1109/TASL.2007.898454</a>.","short":"E. Warsitz, R. Haeb-Umbach, IEEE Transactions on Audio, Speech, and Language Processing 15 (2007) 1529–1539.","apa":"Warsitz, E., &#38; Haeb-Umbach, R. (2007). Blind Acoustic Beamforming Based on Generalized Eigenvalue Decomposition. <i>IEEE Transactions on Audio, Speech, and Language Processing</i>, <i>15</i>(5), 1529–1539. <a href=\"https://doi.org/10.1109/TASL.2007.898454\">https://doi.org/10.1109/TASL.2007.898454</a>","ama":"Warsitz E, Haeb-Umbach R. Blind Acoustic Beamforming Based on Generalized Eigenvalue Decomposition. <i>IEEE Transactions on Audio, Speech, and Language Processing</i>. 2007;15(5):1529-1539. doi:<a href=\"https://doi.org/10.1109/TASL.2007.898454\">10.1109/TASL.2007.898454</a>","ieee":"E. Warsitz and R. Haeb-Umbach, “Blind Acoustic Beamforming Based on Generalized Eigenvalue Decomposition,” <i>IEEE Transactions on Audio, Speech, and Language Processing</i>, vol. 15, no. 5, pp. 1529–1539, 2007.","chicago":"Warsitz, Ernst, and Reinhold Haeb-Umbach. “Blind Acoustic Beamforming Based on Generalized Eigenvalue Decomposition.” <i>IEEE Transactions on Audio, Speech, and Language Processing</i> 15, no. 5 (2007): 1529–39. <a href=\"https://doi.org/10.1109/TASL.2007.898454\">https://doi.org/10.1109/TASL.2007.898454</a>."},"intvolume":"        15","page":"1529-1539"},{"_id":"9535","department":[{"_id":"151"}],"user_id":"55222","keyword":["Noise","Vibration engineering"],"language":[{"iso":"eng"}],"publication":"Proceedings of ISMA - International conference on noise and vibration engineering","type":"conference","status":"public","date_updated":"2022-01-06T07:04:16Z","date_created":"2019-04-29T08:54:27Z","author":[{"full_name":"Genzo, Alexander","last_name":"Genzo","first_name":"Alexander"},{"full_name":"Sextro, Walter","id":"21220","last_name":"Sextro","first_name":"Walter"}],"title":"Dynamic Behaviour of Elastic Bodies Coupled by Extended Friction Contacts","year":"2006","page":"51-52","citation":{"ama":"Genzo A, Sextro W. Dynamic Behaviour of Elastic Bodies Coupled by Extended Friction Contacts. In: <i>Proceedings of ISMA - International Conference on Noise and Vibration Engineering</i>. ; 2006:51-52.","chicago":"Genzo, Alexander, and Walter Sextro. “Dynamic Behaviour of Elastic Bodies Coupled by Extended Friction Contacts.” In <i>Proceedings of ISMA - International Conference on Noise and Vibration Engineering</i>, 51–52, 2006.","ieee":"A. Genzo and W. Sextro, “Dynamic Behaviour of Elastic Bodies Coupled by Extended Friction Contacts,” in <i>Proceedings of ISMA - International conference on noise and vibration engineering</i>, 2006, pp. 51–52.","apa":"Genzo, A., &#38; Sextro, W. (2006). Dynamic Behaviour of Elastic Bodies Coupled by Extended Friction Contacts. In <i>Proceedings of ISMA - International conference on noise and vibration engineering</i> (pp. 51–52).","short":"A. Genzo, W. Sextro, in: Proceedings of ISMA - International Conference on Noise and Vibration Engineering, 2006, pp. 51–52.","bibtex":"@inproceedings{Genzo_Sextro_2006, title={Dynamic Behaviour of Elastic Bodies Coupled by Extended Friction Contacts}, booktitle={Proceedings of ISMA - International conference on noise and vibration engineering}, author={Genzo, Alexander and Sextro, Walter}, year={2006}, pages={51–52} }","mla":"Genzo, Alexander, and Walter Sextro. “Dynamic Behaviour of Elastic Bodies Coupled by Extended Friction Contacts.” <i>Proceedings of ISMA - International Conference on Noise and Vibration Engineering</i>, 2006, pp. 51–52."}},{"department":[{"_id":"54"}],"user_id":"44006","_id":"11943","language":[{"iso":"eng"}],"keyword":["clean speech training data","iterative methods","iterative speech enhancement","Kalman filter","Kalman filters","Kalman-LM-iterative algorithm","line spectral pair parameters","log-spectral distance","marginalized particle filter","noise level","nonlinear dynamic state speech model","particle filtering (numerical methods)","single channel speech enhancement","SNR gains","speech enhancement","speech samples"],"publication":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2006)","type":"conference","status":"public","abstract":[{"text":"A marginalized particle filter is proposed for performing single channel speech enhancement with a non-linear dynamic state model. The system consists of a particle filter for tracking line spectral pair (LSP) parameters and a Kalman filter per particle for speech enhancement. The state model for the LSPs has been learnt on clean speech training data. In our approach parameters and speech samples are processed at different time scales by assuming the parameters to be constant for small blocks of data. Further enhancement is obtained by an iteration which can be applied on these small blocks. The experiments show that similar SNR gains are obtained as with the Kalman-LM-iterative algorithm. However better values of the noise level and the log-spectral distance are achieved","lang":"eng"}],"volume":1,"date_created":"2019-07-12T05:31:15Z","author":[{"full_name":"Windmann, Stefan","last_name":"Windmann","first_name":"Stefan"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","id":"242","full_name":"Haeb-Umbach, Reinhold"}],"oa":"1","date_updated":"2022-01-06T06:51:12Z","doi":"10.1109/ICASSP.2006.1660058","main_file_link":[{"open_access":"1","url":"https://groups.uni-paderborn.de/nt/pubs/2006/WiHa06-2.pdf"}],"title":"Iterative Speech Enhancement using a Non-Linear Dynamic State Model of Speech and its Parameters","page":"I","intvolume":"         1","citation":{"ama":"Windmann S, Haeb-Umbach R. Iterative Speech Enhancement using a Non-Linear Dynamic State Model of Speech and its Parameters. In: <i>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2006)</i>. Vol 1. ; 2006:I. doi:<a href=\"https://doi.org/10.1109/ICASSP.2006.1660058\">10.1109/ICASSP.2006.1660058</a>","chicago":"Windmann, Stefan, and Reinhold Haeb-Umbach. “Iterative Speech Enhancement Using a Non-Linear Dynamic State Model of Speech and Its Parameters.” In <i>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2006)</i>, 1:I, 2006. <a href=\"https://doi.org/10.1109/ICASSP.2006.1660058\">https://doi.org/10.1109/ICASSP.2006.1660058</a>.","ieee":"S. Windmann and R. Haeb-Umbach, “Iterative Speech Enhancement using a Non-Linear Dynamic State Model of Speech and its Parameters,” in <i>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2006)</i>, 2006, vol. 1, p. I.","short":"S. Windmann, R. Haeb-Umbach, in: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2006), 2006, p. I.","bibtex":"@inproceedings{Windmann_Haeb-Umbach_2006, title={Iterative Speech Enhancement using a Non-Linear Dynamic State Model of Speech and its Parameters}, volume={1}, DOI={<a href=\"https://doi.org/10.1109/ICASSP.2006.1660058\">10.1109/ICASSP.2006.1660058</a>}, booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2006)}, author={Windmann, Stefan and Haeb-Umbach, Reinhold}, year={2006}, pages={I} }","mla":"Windmann, Stefan, and Reinhold Haeb-Umbach. “Iterative Speech Enhancement Using a Non-Linear Dynamic State Model of Speech and Its Parameters.” <i>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2006)</i>, vol. 1, 2006, p. I, doi:<a href=\"https://doi.org/10.1109/ICASSP.2006.1660058\">10.1109/ICASSP.2006.1660058</a>.","apa":"Windmann, S., &#38; Haeb-Umbach, R. (2006). Iterative Speech Enhancement using a Non-Linear Dynamic State Model of Speech and its Parameters. In <i>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2006)</i> (Vol. 1, p. I). <a href=\"https://doi.org/10.1109/ICASSP.2006.1660058\">https://doi.org/10.1109/ICASSP.2006.1660058</a>"},"year":"2006"}]