[{"publication_identifier":{"issn":["2329-9290"]},"issue":"1","year":"2014","citation":{"short":"V. Leutnant, A. Krueger, R. Haeb-Umbach, IEEE/ACM Transactions on Audio, Speech, and Language Processing 22 (2014) 95–109.","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} }","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>","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.","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>.","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>"},"page":"95-109","intvolume":"        22","date_updated":"2022-01-06T06:51:11Z","author":[{"full_name":"Leutnant, Volker","last_name":"Leutnant","first_name":"Volker"},{"full_name":"Krueger, Alexander","last_name":"Krueger","first_name":"Alexander"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242"}],"date_created":"2019-07-12T05:29:41Z","volume":22,"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","type":"journal_article","publication":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","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","_id":"11861","user_id":"44006","department":[{"_id":"54"}],"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"}]},{"doi":"10.1109/TASL.2010.2049684","main_file_link":[{"url":"https://groups.uni-paderborn.de/nt/pubs/2010/KrHa10.pdf","open_access":"1"}],"oa":"1","date_updated":"2022-01-06T06:51:11Z","volume":18,"author":[{"first_name":"Alexander","full_name":"Krueger, Alexander","last_name":"Krueger"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"page":"1692-1707","intvolume":"        18","citation":{"ama":"Krueger A, Haeb-Umbach R. Model-Based Feature Enhancement for Reverberant Speech Recognition. <i>IEEE Transactions on Audio, Speech, and Language Processing</i>. 2010;18(7):1692-1707. doi:<a href=\"https://doi.org/10.1109/TASL.2010.2049684\">10.1109/TASL.2010.2049684</a>","chicago":"Krueger, Alexander, and Reinhold Haeb-Umbach. “Model-Based Feature Enhancement for Reverberant Speech Recognition.” <i>IEEE Transactions on Audio, Speech, and Language Processing</i> 18, no. 7 (2010): 1692–1707. <a href=\"https://doi.org/10.1109/TASL.2010.2049684\">https://doi.org/10.1109/TASL.2010.2049684</a>.","ieee":"A. Krueger and R. Haeb-Umbach, “Model-Based Feature Enhancement for Reverberant Speech Recognition,” <i>IEEE Transactions on Audio, Speech, and Language Processing</i>, vol. 18, no. 7, pp. 1692–1707, 2010.","apa":"Krueger, A., &#38; Haeb-Umbach, R. (2010). Model-Based Feature Enhancement for Reverberant Speech Recognition. <i>IEEE Transactions on Audio, Speech, and Language Processing</i>, <i>18</i>(7), 1692–1707. <a href=\"https://doi.org/10.1109/TASL.2010.2049684\">https://doi.org/10.1109/TASL.2010.2049684</a>","bibtex":"@article{Krueger_Haeb-Umbach_2010, title={Model-Based Feature Enhancement for Reverberant Speech Recognition}, volume={18}, DOI={<a href=\"https://doi.org/10.1109/TASL.2010.2049684\">10.1109/TASL.2010.2049684</a>}, number={7}, journal={IEEE Transactions on Audio, Speech, and Language Processing}, author={Krueger, Alexander and Haeb-Umbach, Reinhold}, year={2010}, pages={1692–1707} }","short":"A. Krueger, R. Haeb-Umbach, IEEE Transactions on Audio, Speech, and Language Processing 18 (2010) 1692–1707.","mla":"Krueger, Alexander, and Reinhold Haeb-Umbach. “Model-Based Feature Enhancement for Reverberant Speech Recognition.” <i>IEEE Transactions on Audio, Speech, and Language Processing</i>, vol. 18, no. 7, 2010, pp. 1692–707, doi:<a href=\"https://doi.org/10.1109/TASL.2010.2049684\">10.1109/TASL.2010.2049684</a>."},"_id":"11846","department":[{"_id":"54"}],"user_id":"44006","status":"public","type":"journal_article","title":"Model-Based Feature Enhancement for Reverberant Speech Recognition","date_created":"2019-07-12T05:29:23Z","year":"2010","issue":"7","keyword":["ASR","AURORA5 database","automatic speech recognition","Bayesian inference","belief networks","CMLLR","computational complexity","constrained maximum likelihood linear regression","least mean squares methods","LMPSC computation","logarithmic Mel power spectrum","maximum likelihood estimation","Mel frequency cepstral coefficients","MFCC feature vectors","microphone signal","minimum mean square error estimation","model-based feature enhancement","regression analysis","reverberant speech recognition","reverberation","RIR energy","room impulse response","speech recognition","stochastic observation model","stochastic processes"],"language":[{"iso":"eng"}],"abstract":[{"text":"In this paper, we present a new technique for automatic speech recognition (ASR) in reverberant environments. Our approach is aimed at the enhancement of the logarithmic Mel power spectrum, which is computed at an intermediate stage to obtain the widely used Mel frequency cepstral coefficients (MFCCs). Given the reverberant logarithmic Mel power spectral coefficients (LMPSCs), a minimum mean square error estimate of the clean LMPSCs is computed by carrying out Bayesian inference. We employ switching linear dynamical models as an a priori model for the dynamics of the clean LMPSCs. Further, we derive a stochastic observation model which relates the clean to the reverberant LMPSCs through a simplified model of the room impulse response (RIR). This model requires only two parameters, namely RIR energy and reverberation time, which can be estimated from the captured microphone signal. The performance of the proposed enhancement technique is studied on the AURORA5 database and compared to that of constrained maximum-likelihood linear regression (CMLLR). It is shown by experimental results that our approach significantly outperforms CMLLR and that up to 80\\% of the errors caused by the reverberation are recovered. In addition to the fact that the approach is compatible with the standard MFCC feature vectors, it leaves the ASR back-end unchanged. It is of moderate computational complexity and suitable for real time applications.","lang":"eng"}],"publication":"IEEE Transactions on Audio, Speech, and Language Processing"},{"keyword":["computational complexity","expectation-maximisation algorithm","Global Positioning System","inertial measurement unit","inertial navigation","interacting multiple model","iterative block expectation-maximization algorithm","Kalman filters","multi-stage Kalman filter","parameter estimation","road vehicles","vehicle positioning","vehicle tracking"],"language":[{"iso":"eng"}],"_id":"11724","user_id":"44006","department":[{"_id":"54"}],"abstract":[{"text":"In this paper we present a novel vehicle tracking method which is based on multi-stage Kalman filtering of GPS and IMU sensor data. After individual Kalman filtering of GPS and IMU measurements the estimates of the orientation of the vehicle are combined in an optimal manner to improve the robustness towards drift errors. The tracking algorithm incorporates the estimation of time-variant covariance parameters by using an iterative block Expectation-Maximization algorithm to account for time-variant driving conditions and measurement quality. The proposed system is compared to an interacting multiple model approach (IMM) and achieves improved localization accuracy at lower computational complexity. Furthermore we show how the joint parameter estimation and localizaiton can be conducted with streaming input data to be able to track vehicles in a real driving environment.","lang":"eng"}],"status":"public","type":"conference","publication":"IEEE 69th Vehicular Technology Conference (VTC 2009 Spring)","title":"Joint Parameter Estimation and Tracking in a Multi-Stage Kalman Filter for Vehicle Positioning","main_file_link":[{"open_access":"1","url":"https://groups.uni-paderborn.de/nt/pubs/2009/BePeHa09-1.pdf"}],"doi":"10.1109/VETECS.2009.5073634","date_updated":"2022-01-06T06:51:07Z","oa":"1","date_created":"2019-07-12T05:27:02Z","author":[{"last_name":"Bevermeier","full_name":"Bevermeier, Maik","first_name":"Maik"},{"first_name":"Sven","last_name":"Peschke","full_name":"Peschke, Sven"},{"first_name":"Reinhold","full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach"}],"year":"2009","citation":{"ama":"Bevermeier M, Peschke S, Haeb-Umbach R. Joint Parameter Estimation and Tracking in a Multi-Stage Kalman Filter for Vehicle Positioning. In: <i>IEEE 69th Vehicular Technology Conference (VTC 2009 Spring)</i>. ; 2009:1-5. doi:<a href=\"https://doi.org/10.1109/VETECS.2009.5073634\">10.1109/VETECS.2009.5073634</a>","ieee":"M. Bevermeier, S. Peschke, and R. Haeb-Umbach, “Joint Parameter Estimation and Tracking in a Multi-Stage Kalman Filter for Vehicle Positioning,” in <i>IEEE 69th Vehicular Technology Conference (VTC 2009 Spring)</i>, 2009, pp. 1–5.","chicago":"Bevermeier, Maik, Sven Peschke, and Reinhold Haeb-Umbach. “Joint Parameter Estimation and Tracking in a Multi-Stage Kalman Filter for Vehicle Positioning.” In <i>IEEE 69th Vehicular Technology Conference (VTC 2009 Spring)</i>, 1–5, 2009. <a href=\"https://doi.org/10.1109/VETECS.2009.5073634\">https://doi.org/10.1109/VETECS.2009.5073634</a>.","apa":"Bevermeier, M., Peschke, S., &#38; Haeb-Umbach, R. (2009). Joint Parameter Estimation and Tracking in a Multi-Stage Kalman Filter for Vehicle Positioning. In <i>IEEE 69th Vehicular Technology Conference (VTC 2009 Spring)</i> (pp. 1–5). <a href=\"https://doi.org/10.1109/VETECS.2009.5073634\">https://doi.org/10.1109/VETECS.2009.5073634</a>","short":"M. Bevermeier, S. Peschke, R. Haeb-Umbach, in: IEEE 69th Vehicular Technology Conference (VTC 2009 Spring), 2009, pp. 1–5.","bibtex":"@inproceedings{Bevermeier_Peschke_Haeb-Umbach_2009, title={Joint Parameter Estimation and Tracking in a Multi-Stage Kalman Filter for Vehicle Positioning}, DOI={<a href=\"https://doi.org/10.1109/VETECS.2009.5073634\">10.1109/VETECS.2009.5073634</a>}, booktitle={IEEE 69th Vehicular Technology Conference (VTC 2009 Spring)}, author={Bevermeier, Maik and Peschke, Sven and Haeb-Umbach, Reinhold}, year={2009}, pages={1–5} }","mla":"Bevermeier, Maik, et al. “Joint Parameter Estimation and Tracking in a Multi-Stage Kalman Filter for Vehicle Positioning.” <i>IEEE 69th Vehicular Technology Conference (VTC 2009 Spring)</i>, 2009, pp. 1–5, doi:<a href=\"https://doi.org/10.1109/VETECS.2009.5073634\">10.1109/VETECS.2009.5073634</a>."},"page":"1-5"}]