[{"page":"1640-1652","intvolume":"        21","citation":{"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.","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>","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>","short":"V. Leutnant, A. Krueger, R. Haeb-Umbach, IEEE Transactions on Audio, Speech, and Language Processing 21 (2013) 1640–1652.","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} }","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>."},"year":"2013","issue":"8","doi":"10.1109/TASL.2013.2258013","title":"Bayesian Feature Enhancement for Reverberation and Noise Robust Speech Recognition","volume":21,"author":[{"full_name":"Leutnant, Volker","last_name":"Leutnant","first_name":"Volker"},{"full_name":"Krueger, Alexander","last_name":"Krueger","first_name":"Alexander"},{"full_name":"Haeb-Umbach, Reinhold","id":"242","last_name":"Haeb-Umbach","first_name":"Reinhold"}],"date_created":"2019-07-12T05:29:42Z","date_updated":"2022-01-06T06:51:11Z","status":"public","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."}],"publication":"IEEE Transactions on Audio, Speech, and Language Processing","type":"journal_article","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"],"department":[{"_id":"54"}],"user_id":"44006","_id":"11862"},{"status":"public","abstract":[{"lang":"eng","text":"Amongst several data driven approaches for designing filters for the time sequence of spectral parameters, the linear discriminant analysis (LDA) based method has been proposed for automatic speech recognition. Here we apply LDA-based filter design to cepstral features, which better match the inherent assumption of this method that feature vector components are uncorrelated. Extensive recognition experiments have been conducted both on the standard TIMIT phone recognition task and on a proprietary 130-words command word task under various adverse environmental conditions, including reverberant data with real-life room impulse responses and data processed by acoustic echo cancellation algorithms. Significant error rate reductions have been achieved when applying the novel long-range feature filters compared to standard approaches employing cepstral mean normalization and delta and delta-delta features, in particular when facing acoustic echo cancellation scenarios and room reverberation. For example, the phone accuracy on reverberated TIMIT data could be increased from 50.7\\% to 56.0\\%"}],"publication":"IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2000)","type":"conference","language":[{"iso":"eng"}],"keyword":["acoustic echo cancellation algorithms","adverse environmental conditions","automatic speech recognition","cepstral analysis","cepstral features","cepstral mean normalization","command word task","delta-delta features","delta features","echo suppression","error rate reductions","feature vector components","FIR filters","LDA derived cepstral trajectory filters","linear discriminant analysis","long-range feature filters","phone accuracy","real-life room impulse responses","reverberant data","spectral parameters","speech recognition","standard TIMIT phone recognition task"],"department":[{"_id":"54"}],"user_id":"44006","_id":"11869","intvolume":"         2","page":"II1105-II1108 vol.2","citation":{"mla":"Lieb, M., and Reinhold Haeb-Umbach. “LDA Derived Cepstral Trajectory Filters in Adverse Environmental Conditions.” <i>IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2000)</i>, vol. 2, 2000, pp. II1105-II1108 vol.2, doi:<a href=\"https://doi.org/10.1109/ICASSP.2000.859157\">10.1109/ICASSP.2000.859157</a>.","short":"M. Lieb, R. Haeb-Umbach, in: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2000), 2000, pp. II1105-II1108 vol.2.","bibtex":"@inproceedings{Lieb_Haeb-Umbach_2000, title={LDA derived cepstral trajectory filters in adverse environmental conditions}, volume={2}, DOI={<a href=\"https://doi.org/10.1109/ICASSP.2000.859157\">10.1109/ICASSP.2000.859157</a>}, booktitle={IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2000)}, author={Lieb, M. and Haeb-Umbach, Reinhold}, year={2000}, pages={II1105-II1108 vol.2} }","apa":"Lieb, M., &#38; Haeb-Umbach, R. (2000). LDA derived cepstral trajectory filters in adverse environmental conditions. In <i>IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2000)</i> (Vol. 2, pp. II1105-II1108 vol.2). <a href=\"https://doi.org/10.1109/ICASSP.2000.859157\">https://doi.org/10.1109/ICASSP.2000.859157</a>","ama":"Lieb M, Haeb-Umbach R. LDA derived cepstral trajectory filters in adverse environmental conditions. In: <i>IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2000)</i>. Vol 2. ; 2000:II1105-II1108 vol.2. doi:<a href=\"https://doi.org/10.1109/ICASSP.2000.859157\">10.1109/ICASSP.2000.859157</a>","chicago":"Lieb, M., and Reinhold Haeb-Umbach. “LDA Derived Cepstral Trajectory Filters in Adverse Environmental Conditions.” In <i>IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2000)</i>, 2:II1105-II1108 vol.2, 2000. <a href=\"https://doi.org/10.1109/ICASSP.2000.859157\">https://doi.org/10.1109/ICASSP.2000.859157</a>.","ieee":"M. Lieb and R. Haeb-Umbach, “LDA derived cepstral trajectory filters in adverse environmental conditions,” in <i>IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2000)</i>, 2000, vol. 2, pp. II1105-II1108 vol.2."},"year":"2000","doi":"10.1109/ICASSP.2000.859157","main_file_link":[{"open_access":"1","url":"https://groups.uni-paderborn.de/nt/pubs/2000/LiHa00.pdf"}],"title":"LDA derived cepstral trajectory filters in adverse environmental conditions","volume":2,"author":[{"first_name":"M.","last_name":"Lieb","full_name":"Lieb, M."},{"first_name":"Reinhold","id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach"}],"date_created":"2019-07-12T05:29:50Z","date_updated":"2022-01-06T06:51:11Z","oa":"1"}]