[{"department":[{"_id":"54"}],"oa":"1","type":"conference","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"],"date_created":"2019-07-12T05:28:45Z","abstract":[{"lang":"eng","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."}],"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>","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.","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>.","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.","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>","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} }"},"publication":"Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on","user_id":"44006","doi":"10.1109/ICASSP.2015.7178933","_id":"11813","language":[{"iso":"eng"}],"main_file_link":[{"url":"https://groups.uni-paderborn.de/nt/pubs/2015/hey_icassp_2015.pdf","open_access":"1"}],"page":"5053-5057","date_updated":"2022-01-06T06:51:09Z","author":[{"id":"9168","full_name":"Heymann, Jahn","last_name":"Heymann","first_name":"Jahn"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242"},{"full_name":"Golik, P.","last_name":"Golik","first_name":"P."},{"last_name":"Schlueter","first_name":"R.","full_name":"Schlueter, R."}],"year":"2015","status":"public","title":"Unsupervised adaptation of a denoising autoencoder by Bayesian Feature Enhancement for reverberant asr under mismatch conditions"},{"oa":"1","citation":{"chicago":"Ion, Valentin, and Reinhold Haeb-Umbach. “A Novel Uncertainty Decoding Rule With Applications to Transmission Error Robust Speech Recognition.” <i>IEEE Transactions on Audio, Speech, and Language Processing</i> 16, no. 5 (2008): 1047–60. <a href=\"https://doi.org/10.1109/TASL.2008.925879\">https://doi.org/10.1109/TASL.2008.925879</a>.","short":"V. Ion, R. Haeb-Umbach, IEEE Transactions on Audio, Speech, and Language Processing 16 (2008) 1047–1060.","apa":"Ion, V., &#38; Haeb-Umbach, R. (2008). A Novel Uncertainty Decoding Rule With Applications to Transmission Error Robust Speech Recognition. <i>IEEE Transactions on Audio, Speech, and Language Processing</i>, <i>16</i>(5), 1047–1060. <a href=\"https://doi.org/10.1109/TASL.2008.925879\">https://doi.org/10.1109/TASL.2008.925879</a>","ieee":"V. Ion and R. Haeb-Umbach, “A Novel Uncertainty Decoding Rule With Applications to Transmission Error Robust Speech Recognition,” <i>IEEE Transactions on Audio, Speech, and Language Processing</i>, vol. 16, no. 5, pp. 1047–1060, 2008.","ama":"Ion V, Haeb-Umbach R. A Novel Uncertainty Decoding Rule With Applications to Transmission Error Robust Speech Recognition. <i>IEEE Transactions on Audio, Speech, and Language Processing</i>. 2008;16(5):1047-1060. doi:<a href=\"https://doi.org/10.1109/TASL.2008.925879\">10.1109/TASL.2008.925879</a>","bibtex":"@article{Ion_Haeb-Umbach_2008, title={A Novel Uncertainty Decoding Rule With Applications to Transmission Error Robust Speech Recognition}, volume={16}, DOI={<a href=\"https://doi.org/10.1109/TASL.2008.925879\">10.1109/TASL.2008.925879</a>}, number={5}, journal={IEEE Transactions on Audio, Speech, and Language Processing}, author={Ion, Valentin and Haeb-Umbach, Reinhold}, year={2008}, pages={1047–1060} }","mla":"Ion, Valentin, and Reinhold Haeb-Umbach. “A Novel Uncertainty Decoding Rule With Applications to Transmission Error Robust Speech Recognition.” <i>IEEE Transactions on Audio, Speech, and Language Processing</i>, vol. 16, no. 5, 2008, pp. 1047–60, doi:<a href=\"https://doi.org/10.1109/TASL.2008.925879\">10.1109/TASL.2008.925879</a>."},"user_id":"44006","volume":16,"page":"1047-1060","_id":"11820","status":"public","keyword":["automatic speech recognition","bit errors","codecs","communication links","corrupted observations","decoding","distributed speech recognition","error-prone communication network","feature vector sequence","hidden Markov model-based ASR","hidden Markov models","inter-frame correlation","Internet telephony","network speech recognition","packet loss","speech posterior","speech recognition","transmission error robust speech recognition","uncertainty decoding","voice-over-IP codecs"],"type":"journal_article","department":[{"_id":"54"}],"date_created":"2019-07-12T05:28:53Z","abstract":[{"lang":"eng","text":"In this paper, we derive an uncertainty decoding rule for automatic speech recognition (ASR), which accounts for both corrupted observations and inter-frame correlation. The conditional independence assumption, prevalent in hidden Markov model-based ASR, is relaxed to obtain a clean speech posterior that is conditioned on the complete observed feature vector sequence. This is a more informative posterior than one conditioned only on the current observation. The novel decoding is used to obtain a transmission-error robust remote ASR system, where the speech capturing unit is connected to the decoder via an error-prone communication network. We show how the clean speech posterior can be computed for communication links being characterized by either bit errors or packet loss. Recognition results are presented for both distributed and network speech recognition, where in the latter case common voice-over-IP codecs are employed."}],"publication":"IEEE Transactions on Audio, Speech, and Language Processing","issue":"5","doi":"10.1109/TASL.2008.925879","main_file_link":[{"open_access":"1","url":"https://groups.uni-paderborn.de/nt/pubs/2008/IoHa08-1.pdf"}],"language":[{"iso":"eng"}],"date_updated":"2022-01-06T06:51:10Z","intvolume":"        16","year":"2008","title":"A Novel Uncertainty Decoding Rule With Applications to Transmission Error Robust Speech Recognition","author":[{"last_name":"Ion","first_name":"Valentin","full_name":"Ion, Valentin"},{"full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold","id":"242"}]},{"language":[{"iso":"eng"}],"main_file_link":[{"url":"https://groups.uni-paderborn.de/nt/pubs/2005/IoHa05-2.pdf","open_access":"1"}],"doi":"10.1109/ICASSP.2005.1415118","author":[{"first_name":"Valentin","last_name":"Ion","full_name":"Ion, Valentin"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","first_name":"Reinhold","last_name":"Haeb-Umbach"}],"title":"A Comparison of Soft-Feature Distributed Speech Recognition with Candidate Codecs for Speech Enabled Mobile Services","year":"2005","intvolume":"         1","date_updated":"2022-01-06T06:51:10Z","date_created":"2019-07-12T05:29:02Z","department":[{"_id":"54"}],"type":"conference","keyword":["adaptive codes","adaptive multirate codec","AMR","distributed speech recognition","ETSI","extended advanced front-end","recognition performance","SFDSR","simulated GSM transmission","soft-feature distributed speech recognition","speech codecs","speech coding","speech recognition","variable rate codes","XAFE"],"publication":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2005)","abstract":[{"text":"In this paper we present a comparison of the recently proposed Soft-Feature Distributed Speech Recognition (SFDSR) with the two evaluated candidate codecs for Speech Enabled Services over wireless networks: Adaptive Multirate Codec (AMR) and the ETSI Extended Advanced Front-End for Distributed Speech Recognition (XAFE). It is shown that SFDSR achieves the best recognition performance on a simulated GSM transmission, followed by XAFE and AMR.We also present some new results concerning SFDSR which demonstrate the versatility of the approach. Further, a simple method is introduced which considerably reduces the computational effort.","lang":"eng"}],"_id":"11828","page":"333-336","volume":1,"user_id":"44006","status":"public","oa":"1","citation":{"apa":"Ion, V., &#38; Haeb-Umbach, R. (2005). A Comparison of Soft-Feature Distributed Speech Recognition with Candidate Codecs for Speech Enabled Mobile Services. In <i>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2005)</i> (Vol. 1, pp. 333–336). <a href=\"https://doi.org/10.1109/ICASSP.2005.1415118\">https://doi.org/10.1109/ICASSP.2005.1415118</a>","ieee":"V. Ion and R. Haeb-Umbach, “A Comparison of Soft-Feature Distributed Speech Recognition with Candidate Codecs for Speech Enabled Mobile Services,” in <i>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2005)</i>, 2005, vol. 1, pp. 333–336.","chicago":"Ion, Valentin, and Reinhold Haeb-Umbach. “A Comparison of Soft-Feature Distributed Speech Recognition with Candidate Codecs for Speech Enabled Mobile Services.” In <i>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2005)</i>, 1:333–36, 2005. <a href=\"https://doi.org/10.1109/ICASSP.2005.1415118\">https://doi.org/10.1109/ICASSP.2005.1415118</a>.","short":"V. Ion, R. Haeb-Umbach, in: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2005), 2005, pp. 333–336.","mla":"Ion, Valentin, and Reinhold Haeb-Umbach. “A Comparison of Soft-Feature Distributed Speech Recognition with Candidate Codecs for Speech Enabled Mobile Services.” <i>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2005)</i>, vol. 1, 2005, pp. 333–36, doi:<a href=\"https://doi.org/10.1109/ICASSP.2005.1415118\">10.1109/ICASSP.2005.1415118</a>.","ama":"Ion V, Haeb-Umbach R. A Comparison of Soft-Feature Distributed Speech Recognition with Candidate Codecs for Speech Enabled Mobile Services. In: <i>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2005)</i>. Vol 1. ; 2005:333-336. doi:<a href=\"https://doi.org/10.1109/ICASSP.2005.1415118\">10.1109/ICASSP.2005.1415118</a>","bibtex":"@inproceedings{Ion_Haeb-Umbach_2005, title={A Comparison of Soft-Feature Distributed Speech Recognition with Candidate Codecs for Speech Enabled Mobile Services}, volume={1}, DOI={<a href=\"https://doi.org/10.1109/ICASSP.2005.1415118\">10.1109/ICASSP.2005.1415118</a>}, booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2005)}, author={Ion, Valentin and Haeb-Umbach, Reinhold}, year={2005}, pages={333–336} }"}}]