[{"oa":"1","citation":{"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>","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.","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>.","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>.","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>","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} }"},"volume":18,"user_id":"44006","_id":"11846","page":"1692-1707","status":"public","department":[{"_id":"54"}],"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"],"type":"journal_article","date_created":"2019-07-12T05:29:23Z","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"}],"issue":"7","publication":"IEEE Transactions on Audio, Speech, and Language Processing","doi":"10.1109/TASL.2010.2049684","language":[{"iso":"eng"}],"main_file_link":[{"url":"https://groups.uni-paderborn.de/nt/pubs/2010/KrHa10.pdf","open_access":"1"}],"intvolume":"        18","date_updated":"2022-01-06T06:51:11Z","author":[{"last_name":"Krueger","first_name":"Alexander","full_name":"Krueger, Alexander"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"year":"2010","title":"Model-Based Feature Enhancement for Reverberant Speech Recognition"},{"date_created":"2019-07-12T05:28:58Z","department":[{"_id":"54"}],"type":"conference","keyword":["distributed speech recognition","least mean squares methods","MAP estimate","maximum likelihood estimation","MMSE estimate","packet loss compensation scheme","packet switched communication","posteriori probability density function","robust error mitigation method","soft-features","speech recognition","table lookup","voice communication","wireless channels"],"publication":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2006)","abstract":[{"text":"Soft-feature based speech recognition, which is an example of uncertainty decoding, has been proven to be a robust error mitigation method for distributed speech recognition over wireless channels exhibiting bit errors. In this paper we extend this concept to packet-oriented transmissions. The a posteriori probability density function of the lost feature vector, given the closest received neighbours, is computed. In the experiments, the nearest frame repetition, which is shown to be equivalent to the MAP estimate, outperforms the MMSE estimate for long bursts. Taking the variance into account at the speech recognition stage results in superior performance compared to classical schemes using point estimates. A computationally and memory efficient implementation of the proposed packet loss compensation scheme based on table lookup is presented","lang":"eng"}],"language":[{"iso":"eng"}],"main_file_link":[{"url":"https://groups.uni-paderborn.de/nt/pubs/2006/IoHa06-2.pdf","open_access":"1"}],"doi":"10.1109/ICASSP.2006.1659984","author":[{"full_name":"Ion, Valentin","last_name":"Ion","first_name":"Valentin"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","first_name":"Reinhold","last_name":"Haeb-Umbach"}],"year":"2006","title":"An Inexpensive Packet Loss Compensation Scheme for Distributed Speech Recognition Based on Soft-Features","intvolume":"         1","date_updated":"2022-01-06T06:51:10Z","oa":"1","citation":{"bibtex":"@inproceedings{Ion_Haeb-Umbach_2006, title={An Inexpensive Packet Loss Compensation Scheme for Distributed Speech Recognition Based on Soft-Features}, volume={1}, DOI={<a href=\"https://doi.org/10.1109/ICASSP.2006.1659984\">10.1109/ICASSP.2006.1659984</a>}, booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2006)}, author={Ion, Valentin and Haeb-Umbach, Reinhold}, year={2006}, pages={I} }","ama":"Ion V, Haeb-Umbach R. An Inexpensive Packet Loss Compensation Scheme for Distributed Speech Recognition Based on Soft-Features. 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.2006.1659984\">10.1109/ICASSP.2006.1659984</a>","mla":"Ion, Valentin, and Reinhold Haeb-Umbach. “An Inexpensive Packet Loss Compensation Scheme for Distributed Speech Recognition Based on Soft-Features.” <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.2006.1659984\">10.1109/ICASSP.2006.1659984</a>.","chicago":"Ion, Valentin, and Reinhold Haeb-Umbach. “An Inexpensive Packet Loss Compensation Scheme for Distributed Speech Recognition Based on Soft-Features.” 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.2006.1659984\">https://doi.org/10.1109/ICASSP.2006.1659984</a>.","short":"V. Ion, R. Haeb-Umbach, in: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2006), 2006, p. I.","ieee":"V. Ion and R. Haeb-Umbach, “An Inexpensive Packet Loss Compensation Scheme for Distributed Speech Recognition Based on Soft-Features,” in <i>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2006)</i>, 2006, vol. 1, p. I.","apa":"Ion, V., &#38; Haeb-Umbach, R. (2006). An Inexpensive Packet Loss Compensation Scheme for Distributed Speech Recognition Based on Soft-Features. 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.2006.1659984\">https://doi.org/10.1109/ICASSP.2006.1659984</a>"},"_id":"11824","page":"I","volume":1,"user_id":"44006","status":"public"}]