{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T03:10:08Z","timestamp":1741317008303,"version":"3.38.0"},"publisher-location":"Berlin, Heidelberg","reference-count":48,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642213168"},{"type":"electronic","value":"9783642213175"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011]]},"DOI":"10.1007\/978-3-642-21317-5_9","type":"book-chapter","created":{"date-parts":[[2011,7,12]],"date-time":"2011-07-12T13:32:24Z","timestamp":1310477544000},"page":"225-255","source":"Crossref","is-referenced-by-count":1,"title":["Variance Compensation for Recognition of Reverberant Speech with Dereverberation Preprocessing"],"prefix":"10.1007","author":[{"given":"Marc","family":"Delcroix","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomohiro","family":"Nakatani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2011,6,23]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Arrowood, J. and Clements, M.: Using observation uncertainty in HMM decoding. In: Proceedings of International Conferences on Spoken Language Processing (ICSLP\u201902), 3, 1562\u20131564 (2002)","DOI":"10.21437\/ICSLP.2002-42"},{"key":"9_CR2","unstructured":"Astudillo, R. F., Kolossa, D. and Orglmeister, R.: Accounting for the uncertainty of speech estimates in the complex domain for minimum mean square error speech enhancement. In: Proceedings of 10th European Conference on Speech Communication and Technology (Interspeech\u201909), 2491\u20132494 (2009)"},{"issue":"2","key":"9_CR3","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1109\/TASSP.1979.1163209","volume":"27","author":"SF Boll","year":"1979","unstructured":"Boll, S. F.: Suppression of acoustic noise in speech using spectral subtraction. IEEE Transactions on Acoustics, Speech and Signal Processing, 27(2), 113\u2013120 (1979)","journal-title":"IEEE Transactions on Acoustics, Speech and Signal Processing"},{"key":"9_CR4","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1016\/S0167-6393(00)00034-0","volume":"34","author":"MP Cooke","year":"2001","unstructured":"Cooke, M. P., Green, P. D., Josifovski, L. B. and Vizinho, A.: Robust automatic speech recognition with missing and uncertain acoustic data. Speech Communication, 34, 267\u2013285 (2001)","journal-title":"Speech Communication"},{"issue":"2\u20133","key":"9_CR5","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1023\/B:VLSI.0000015096.78139.82","volume":"36","author":"L Couvreur","year":"2004","unstructured":"Couvreur, L. and Couvreur, C.: Blind model selection for automatic speech recognition in reverberant environments. Journal of VLSI Signal Processing Systems, 36(2\u20133), 189\u2013203 (2004)","journal-title":"Journal of VLSI Signal Processing Systems"},{"key":"9_CR6","unstructured":"Delcroix, M., Nakatani, T. and Watanabe, S.: Dynamic feature variance adaptation for robust speech recognition with a speech enhancement pre-processor. In: IEICE Technical Report, SP-105, 55\u201360 (2007)"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Delcroix, M., Nakatani, T. and Watanabe, S.: Combined static and dynamic variance adaptation for efficient interconnection of a speech enhancement pre-processor with speech recognizer. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP\u201908), 4073\u20134076 (2008)","DOI":"10.1109\/ICASSP.2008.4518549"},{"issue":"2","key":"9_CR8","doi-asserted-by":"publisher","first-page":"324","DOI":"10.1109\/TASL.2008.2010214","volume":"17","author":"M Delcroix","year":"2009","unstructured":"Delcroix, M., Nakatani, T. and Watanabe, S.: Static and dynamic variance compensation for recognition of reverberant speech with dereverberation preprocessing. IEEE Transactions on Audio, Speech, and Language Processing, 17(2), 324\u2013334 (2009)","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"3","key":"9_CR9","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1109\/TSA.2005.845814","volume":"13","author":"L Deng","year":"2005","unstructured":"Deng, L., Droppo, J. and Acero, A.: Dynamic compensation of HMM variances using the feature enhancement uncertainty computed from a parametric model of speech distortion. IEEE Transactions on Speech and Audio Processing, 13(3), 412\u2013421 (2005)","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9_CR10","unstructured":"Droppo, J., Acero, A. and Deng, L.: Uncertainty decoding with SPLICE for noise robust speech recognition. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP\u201902), 1, 57\u201360 (2002)"},{"key":"9_CR11","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1006\/csla.1996.0013","volume":"10","author":"MJF Gales","year":"1996","unstructured":"Gales, M. J. F. and Woodland, P. C.: Mean and variance adaptation within the MLLR framework. Computer Speech and Language, 10, 249\u2013264 (1996)","journal-title":"Computer Speech and Language"},{"key":"9_CR12","unstructured":"Gillespie, B. W. and Atlas, L. E.: Acoustic diversity for improved speech recognition in reverberant environments. Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP\u201902), 1, 557\u2013600 (2002)"},{"key":"9_CR13","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1016\/0167-6393(94)00059-J","volume":"16","author":"Y Gong","year":"1995","unstructured":"Gong, Y.: Speech recognition in noisy environments: A survey. Speech Communication, 16, 261\u2013291 (1995)","journal-title":"Speech Communication"},{"issue":"1","key":"9_CR14","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1250\/ast.27.28","volume":"27","author":"T Hikichi","year":"2006","unstructured":"Hikichi, T., Delcroix, M. and Miyoshi, M.: Speech dereverberation algorithm using transfer function estimates with overestimated order. Acoustical Science and Technology, 27(1), 28\u201335 (2006)","journal-title":"Acoustical Science and Technology"},{"key":"9_CR15","unstructured":"Hirsch, H. G. and Pearce, D.: The AURORA experimental framework for the performance evaluations of speech recognition systems under noisy condition. In: Proceedings of The ISCA Tutorial and Research Workshop on Automatic Speech Recognition: Challenges for the New Millenium (ITRW ASR2000), 18\u201320 (2000)"},{"key":"9_CR16","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1016\/j.specom.2007.09.004","volume":"50","author":"HG Hirsch","year":"2008","unstructured":"Hirsch, H. G. and Finster, H.: A new approach for the adaptation of HMMs to reverberation and background noise. Speech Communication, 50, 244\u2013263 (2008)","journal-title":"Speech Communication"},{"issue":"4","key":"9_CR17","doi-asserted-by":"publisher","first-page":"1352","DOI":"10.1109\/TASL.2006.889790","volume":"15","author":"T Hori","year":"2007","unstructured":"Hori, T., Hori, C., Minami, Y. and Nakamura, A.: Efficient WFST-based one-pass decoding with on-the-fly hypothesis rescoring in extremely large vocabulary continuous speech recognition. IEEE Transactions on Speech and Audio Processing, 15 (4), 1352\u20131365 (2007)","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9_CR18","volume-title":"Spoken Language Processing: A Guide to Theory","author":"X Huang","year":"2001","unstructured":"Huang, X., Acero, A. and Hon, H.W.: Spoken Language Processing: A Guide to Theory, Algorithm and System Development. Prentice Hall, New-Jersey (2001)"},{"issue":"5","key":"9_CR19","doi-asserted-by":"publisher","first-page":"1047","DOI":"10.1109\/TASL.2008.925879","volume":"16","author":"V Ion","year":"2008","unstructured":"Ion, V. and Haeb-Umbach, R.: A novel uncertainty decoding rule with applications to transmission error robust speech recognition. IEEE Transactions on Speech and Audio Processing, 16 (5), 1047\u20131060 (2008)","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Kameoka, H., Nakatani, T. and Yoshioka, T.: Robust speech dereverberation based on non-negativity and sparse nature of speech spectrograms. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP\u201909), 45\u201348 (2009)","DOI":"10.1109\/ICASSP.2009.4959516"},{"issue":"4","key":"9_CR21","doi-asserted-by":"publisher","first-page":"534","DOI":"10.1109\/TASL.2008.2009015","volume":"17","author":"K Kinoshita","year":"2009","unstructured":"Kinoshita, K., Delcroix, M., Nakatani T. and Miyoshi, M.: Suppression of late reverberation effect on speech signal using long-term multiple-step linear prediction. IEEE Transactions on Audio, Speech and Language Processing, 17 (4), 534\u2013545 (2009)","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Kolossa, D., Sawada, H., Astudillo, R. F., Orglmeister, R. and Makino, S.: Recognition of convolutive speech mixtures by missing feature techniques for ICA. In: Proceedings of The Asilomar Conference on Signals, Systems, and Computers (ACSSC\u201906), 1397\u20131401 (2006)","DOI":"10.1109\/ACSSC.2006.354987"},{"key":"9_CR23","doi-asserted-by":"crossref","unstructured":"Kolossa, D., Araki, S., Delcroix, M., Nakatani, T., Orglmeister, R. and Makino, S.: Missing feature speech recognition in a meeting situation with maximum SNR beamforming. In: Proceedings of The IEEE International Symposium on Circuits and Systems (ISCAS\u201908), 3218\u20133221 (2008)","DOI":"10.1109\/ISCAS.2008.4542143"},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"Kolossa, D., Klimas A. and Orglmeister, R.: Separation and robust recognition of noisy, convolutive speech mixtures using time-frequency masking and missing data techniques. In: Proceedings of The IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, 82\u201385 (2005)","DOI":"10.1109\/ASPAA.2005.1540174"},{"key":"9_CR25","unstructured":"Krueger, A. and Haeb-Umbach, R.: Model based feature enhancement for automatic speech recognition in reverberant environments. In: Proceedings of 10th European Conference on Speech Communication and Technology (Interspeech\u201909), 1231\u20131234 (2009)"},{"key":"9_CR26","volume-title":"Room Acoustics","author":"H Kuttruff","year":"1991","unstructured":"Kuttruff, H.: Room Acoustics. 3rd ed. (Elsevier Science, London, 1991)","edition":"3"},{"key":"9_CR27","unstructured":"Liao, H. and Gales, M. J. F.: Joint uncertainty decoding for noise robust speech recognition. In: Proceedings of 9th European Conference on Speech Communication and Technology (Interspeech\u201905-Eurospeech), 3129\u20133132 (2005)"},{"key":"9_CR28","unstructured":"Liao, H. and Gales, M. J. F.: Adapative training with joint uncertainty decoding for robust recognition of noisy data. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP\u201907), 4, 389\u2013392 (2007)"},{"key":"9_CR29","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1093\/biomet\/80.2.267","volume":"80","author":"X-L Meng","year":"1993","unstructured":"Meng, X.-L. and Rubin, D. B.: Maximum likelihood estimation via the ECM algorithm: A general framework. Biometrika, 80, 267\u2013278 (1993)","journal-title":"Biometrika"},{"key":"9_CR30","unstructured":"Nakamura, S. and Nishiura, T.: RWCP sound scene database in real acoustical environments. http:\/\/tosa.mri.co.jp\/sounddb\/micarray\/indexe.htm Cited 31 May 2010"},{"key":"9_CR31","unstructured":"Naylor, P. A. and Gaubitch, N. D.: Speech dereverberation. In: Proceedings of International Workshop on Acoustic Echo and Noise Control (IWAENC\u201905), iwaenc05.ele.tue.nl\/proceedings\/papers\/pt03.pdf (2005)"},{"key":"9_CR32","doi-asserted-by":"crossref","unstructured":"Paul, D. B. and Baker, J. M. : The design for the Wall Street Journal-based CSR corpus. In: Proceedings of the Workshop on Speech and Natural Language. 357\u2013362 (1992)","DOI":"10.3115\/1075527.1075614"},{"key":"9_CR33","volume-title":"Discrete-Time Speech Signal Processing","author":"TF Quatieri","year":"2002","unstructured":"Quatieri, T. F.: Discrete-Time Speech Signal Processing. (Prentice Hall, New Jersey, 2002)"},{"issue":"5","key":"9_CR34","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1109\/MSP.2005.1511828","volume":"22","author":"B Raj","year":"2005","unstructured":"Raj, B. and Stern, R. M.: Missing-feature approaches in speech recognition. IEEE Signal Processing Magazine, 22 (5), 101\u2013116 (2005)","journal-title":"IEEE Signal Processing Magazine"},{"key":"9_CR35","doi-asserted-by":"crossref","unstructured":"Raut, C. K., Nishimoto, T. and Sagayama, S.: Model adaptation by state splitting of HMM for long reverberation. In: Proceedings of 9th European Conference on Speech Communication and Technology (Interspeech\u201905-Eurospeech), 277\u2013280 (2005)","DOI":"10.21437\/Interspeech.2005-157"},{"issue":"2","key":"9_CR36","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1109\/89.279273","volume":"2","author":"RC Rose","year":"1994","unstructured":"Rose, R. C., Hofstetter, E. M. and Reynolds, D. A.: Integrated models of signal and background with application to speaker identification in noise. IEEE Transactions on Speech and Audio Processing, 2(2), 245\u2013257 (1994)","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9_CR37","doi-asserted-by":"crossref","unstructured":"Sankar, A. and Lee C.-H.: Robust speech recognition based on stochastic matching. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP\u201995), 1, 121\u2013125 (1995)","DOI":"10.1109\/ICASSP.1995.479288"},{"issue":"3","key":"9_CR38","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1109\/89.496215","volume":"4","author":"A Sankar","year":"1996","unstructured":"Sankar, A. and Lee, C.-H.: A maximum-likelihood approach to stochastic matching for robust speech recognition. IEEE Transactions on Speech and Audio Processing, 4(3), 190\u2013202 (1996)","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9_CR39","doi-asserted-by":"crossref","unstructured":"Schuller, B., Wollmer, M., Moosmayr, T. and Rigoll, G.: Recognition of noisy speech: A comparative survey of robust model architecture and feature enhancement. EURASIP Journal on Audio, Speech, and Music Processing 2009, (2009)","DOI":"10.1155\/2009\/942617"},{"key":"9_CR40","doi-asserted-by":"crossref","unstructured":"Sehr, A. and Kellerman, W.: A new concept for feature-domain dereverberation for robust distant-talking ASR. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP\u201907), 4, 369\u2013372 (2007)","DOI":"10.1109\/ICASSP.2007.366926"},{"key":"9_CR41","doi-asserted-by":"crossref","unstructured":"Sehr, A., Maas, R. and Kellerman, W.: Reverberation model-based decoding in the logmelspec domain for robust distant-talking speech recognition. IEEE Transactions on Audio, Speech, and Language Processing, (To appear) (2010)","DOI":"10.1109\/TASL.2010.2050511"},{"key":"9_CR42","doi-asserted-by":"crossref","first-page":"1502","DOI":"10.1016\/j.specom.2005.12.006","volume":"48","author":"V. Stouten","year":"2006","unstructured":"Stouten, V., Van hamme, H. and Wambacq, P.: Model-based feature enhancement with uncertainty decoding for noise robust ASR. Speech Communication, 48, 1502\u20131514 (2006)","journal-title":"Speech Communication"},{"key":"9_CR43","doi-asserted-by":"crossref","unstructured":"Stouten, V., Van hamme, H. and Wambacq, P.: Accounting for the uncertainty of speech estimates in the context of model-based feature enhancement In: Proceedings of International Conferences on Spoken Language Processing (ICSLP\u201904), 105108 (2004)","DOI":"10.21437\/Interspeech.2004-94"},{"key":"9_CR44","doi-asserted-by":"crossref","unstructured":"Takiguchi, T. and Nishimura, M.: Acoustic model adaptation using first order prediction for reverberant speech. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP\u201904), 1, 869\u2013972 (2004)","DOI":"10.1109\/ICASSP.2004.1326124"},{"key":"9_CR45","unstructured":"Tashev, I. and Allred, D.: Reverberation reduction for improved speech recognition. In: Proceedings of Joint Workshop on Hands-Free Speech Communication and Microphone Arrays (HSCMA\u201905), (2005)"},{"key":"9_CR46","volume-title":"Speech enhancement in reverberant environments","author":"T Yoshioka","year":"2010","unstructured":"Yoshioka, T.: Speech enhancement in reverberant environments. Ph.D. dissertation, Kyoto University (2010)"},{"issue":"2","key":"9_CR47","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1109\/TASL.2008.2009161","volume":"17","author":"M Wolfel","year":"2009","unstructured":"Wolfel, M.: Enhanced speech features by single-channel joint compensation of noise and reverberation. IEEE Transactions on Audio, Speech, and Language Processing, 17(2), 312\u2013323 (2009)","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9_CR48","doi-asserted-by":"publisher","first-page":"774","DOI":"10.1109\/TASL.2006.872616","volume":"14","author":"M Wu","year":"2006","unstructured":"Wu, M. and Wang, D.: A two-stage algorithm for one-microphone reverberant speech enhancement. IEEE Transactions on Audio, Speech, and Language Processing, 14, 774\u2013784 (2006)","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"}],"container-title":["Robust Speech Recognition of Uncertain or Missing Data"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-21317-5_9.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T01:59:46Z","timestamp":1741312786000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-21317-5_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642213168","9783642213175"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-21317-5_9","relation":{},"subject":[],"published":{"date-parts":[[2011]]}}}