[{"_id":"11862","user_id":"44006","department":[{"_id":"54"}],"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"],"language":[{"iso":"eng"}],"type":"journal_article","publication":"IEEE Transactions on Audio, Speech, and Language Processing","abstract":[{"lang":"eng","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."}],"status":"public","date_updated":"2022-01-06T06:51:11Z","author":[{"first_name":"Volker","last_name":"Leutnant","full_name":"Leutnant, Volker"},{"first_name":"Alexander","last_name":"Krueger","full_name":"Krueger, Alexander"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242"}],"date_created":"2019-07-12T05:29:42Z","volume":21,"title":"Bayesian Feature Enhancement for Reverberation and Noise Robust Speech Recognition","doi":"10.1109/TASL.2013.2258013","issue":"8","year":"2013","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>","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>.","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.","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."},"page":"1640-1652","intvolume":"        21"},{"abstract":[{"lang":"eng","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"}],"status":"public","publication":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2006)","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"],"language":[{"iso":"eng"}],"_id":"11824","department":[{"_id":"54"}],"user_id":"44006","year":"2006","page":"I","intvolume":"         1","citation":{"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.","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>.","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>","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>","short":"V. Ion, R. Haeb-Umbach, in: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2006), 2006, p. I.","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} }","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>."},"title":"An Inexpensive Packet Loss Compensation Scheme for Distributed Speech Recognition Based on Soft-Features","doi":"10.1109/ICASSP.2006.1659984","main_file_link":[{"open_access":"1","url":"https://groups.uni-paderborn.de/nt/pubs/2006/IoHa06-2.pdf"}],"date_updated":"2022-01-06T06:51:10Z","oa":"1","volume":1,"date_created":"2019-07-12T05:28:58Z","author":[{"last_name":"Ion","full_name":"Ion, Valentin","first_name":"Valentin"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242"}]}]