{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T20:47:30Z","timestamp":1743108450789,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":88,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642213168"},{"type":"electronic","value":"9783642213175"}],"license":[{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011]]},"DOI":"10.1007\/978-3-642-21317-5_4","type":"book-chapter","created":{"date-parts":[[2011,7,12]],"date-time":"2011-07-12T13:32:24Z","timestamp":1310477544000},"page":"67-99","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Front-End, Back-End, and Hybrid Techniques for Noise-Robust Speech Recognition"],"prefix":"10.1007","author":[{"given":"Li","family":"Deng","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2011,6,23]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"A. Acero: Acoustical and Environmental Robustness in Automatic Speech Recognition. Kluwer Academic Publishers (1993)","DOI":"10.1007\/978-1-4615-3122-7"},{"key":"4_CR2","first-page":"869","volume":"3","author":"A Acero","year":"2000","unstructured":"A. Acero, L. Deng, T. Kristjansson, and J. Zhang: HMM adaptation using vector Taylor series for noisy speech recognition. In: Proc. ICSLP, vol.3, pp. 869-872 (2000)","journal-title":"In: Proc. ICSLP"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"M. Afify, X. Cui, and Y. Gao: Stereo-based stochastic mapping for robust speech recognition. In: Proc. ICASSP (2007)","DOI":"10.5772\/6374"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"T. Anastasakos, J. McDonough, R. Schwartz, and J. Makhoul: A compact model for speaker-adaptive training. In: Proc. ICSLP (1996)","DOI":"10.21437\/ICSLP.1996-253"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"J. Arrowood and M. Clements: Using observation uncertainty in HMM decoding. In: Proc. ICSLP, Denver, Colorado (2002)","DOI":"10.21437\/ICSLP.2002-42"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"R. F. Astudillo, D. Kolossa, and R. Orglmeister: Accounting for the uncertainty of speech estimates in the complex domain for minimum mean squared error speech enhancement. In: Proc. Interspeech (2009)","DOI":"10.21437\/Interspeech.2009-371"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"H. Attias, Li Deng, Alex Acero, and John Platt: A new method for speech denoising and robust speech recognition using probabilistic models for clean speech and for noise. In: Proc. of the Eurospeech Conference (2001)","DOI":"10.21437\/Eurospeech.2001-450"},{"key":"4_CR8","unstructured":"H. Attias, J. Platt, Alex Acero, and Li Deng: Speech denoising and dereverberation using probabilistic models. In: Proc. NIPS (2000)"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"J. Baker, Li Deng, Jim Glass, S. Khudanpur, C.-H. Lee, N. Morgan, and D. O\u2019Shaughnessy: Research developments and directions in speech recognition and understanding. IEEE Signal Processing Magazine, vol. 26, no. 3, pp. 75-80 (2009)","DOI":"10.1109\/MSP.2009.932166"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"J. Baker, Li Deng, S. Khudanpur, C.-H. Lee, J. Glass, N. Morgan, and D. O\u2019Shaughnessy: Updated MINDS report on speech recognition and understanding. IEEE Signal Processing Magazine, vol. 26, no. 4 (2009)","DOI":"10.1109\/MSP.2009.932707"},{"issue":"5","key":"4_CR11","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1109\/MSP.2005.1511827","volume":"22","author":"J Bilmes","year":"2005","unstructured":"J. Bilmes and C. Bartels: Graphical model architectures for speech recognition. IEEE Signal Processing Magazine, vol. 22, no. 5, pp. 89-100 (2005)","journal-title":"IEEE Signal Processing Magazine"},{"key":"4_CR12","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1109\/TASSP.1979.1163209","volume":"27","author":"S.F. Boll","year":"1979","unstructured":"S.F. Boll: Suppression of acoustic noise in speech using spectral subtraction. IEEE Trans. on Acoustics, Speech, and Signal Processing, 27:113-120 (1979)","journal-title":"IEEE Trans. on Acoustics, Speech, and Signal Processing"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"K. Demuynck, X. Zhang, D. Van Compernolle, and H. Van hamme: Feature versus model based noise robustness. In: Proc. Interspeech (2010)","DOI":"10.21437\/Interspeech.2010-269"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"L. Deng: Computational models for auditory speech processing. In: Computational Models of Speech Pattern Processing, (NATO ASI Series), pp. 67-77, Springer Verlag (1999)","DOI":"10.1007\/978-3-642-60087-6_6"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"L. Deng: Computational models for speech production. Computational Models of Speech Pattern Processing, (NATO ASI Series), pp. 199-213, Springer Verlag (1999)","DOI":"10.1007\/978-3-642-60087-6_20"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"L. Deng, D. Yu, and A. Acero: Structured speech modeling. IEEE Trans. on Audio, Speech and Language Processing (Special Issue on Rich Transcription), vol. 14, No. 5, pp. 1492-1504 (2006)","DOI":"10.1109\/TASL.2006.878265"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"L. Deng, A. Acero, M. Plumpe, and X.D. Huang: Large vocabulary speech recognition under adverse acoustic environments. In: Proc. ICSLP, pp. 806-809 (2000)","DOI":"10.21437\/ICSLP.2000-657"},{"key":"4_CR18","unstructured":"L. Deng, A. Acero, L. Jiang, J. Droppo, and X. Huang: High-performance robust speech recognition using stereo training data. In: Proc. ICASSP, Salt Lake City, Utah (2001)"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"L. Deng, J. Droppo, and A. Acero: Exploiting variances in robust feature extraction based on a parametric model of speech distortion. In: Proc. ICSLP (2002)","DOI":"10.21437\/ICSLP.2002-638"},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"Li Deng, Jasha Droppo, and Alex Acero: A Bayesian approach to speech feature enhancement using the dynamic cepstral prior. In: Proc. ICASSP, Orlando, Florida (2002)","DOI":"10.1109\/ICASSP.2002.1005868"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"L. Deng, J. Droppo, and A. Acero: Log-domain speech feature enhancement using sequential MAP noise estimation and a phase-sensitive model of the acoustic environment. In: Proc. ICSLP, Denver, Colorado (2002)","DOI":"10.21437\/ICSLP.2002-270"},{"issue":"8","key":"4_CR22","first-page":"605","volume":"10","author":"L Deng","year":"2002","unstructured":"L. Deng, K. Wang, A. Acero, H. Hon, J. Droppo, C. Boulis, Y. Wang, D. Jacoby, M. Mahajan, C. Chelba, and XD. Huang: Distributed speech processing in MiPad\u2019s multimodal user interface. IEEE Trans. on Speech and Audio Processing, vol. 10, no. 8, pp. 605-619 (2002)","journal-title":"Huang: Distributed speech processing in MiPad\u2019s multimodal user interface. IEEE Trans. on Speech and Audio Processing"},{"issue":"2","key":"4_CR23","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1109\/TSA.2003.820201","volume":"12","author":"L Deng","year":"2004","unstructured":"L. Deng, J. Droppo, and A. Acero: Enhancement of log mel power spectra of speech using a phase-sensitive model of the acoustic environment and sequential estimation of the corrupting noise. IEEE Trans. on Speech and Audio Processing, vol.12, no. 2, pp. 133-143 2004)","journal-title":"IEEE Trans. on Speech and Audio Processing"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Li Deng and Xuedong Huang: Challenges in adopting speech recognition. Communications of the ACM, vol. 47, no. 1, pp. 11-13, (2004)","DOI":"10.1145\/962081.962108"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Li Deng, Jasha Droppo, and Alex Acero: Recursive estimation of nonstationary noise using iterative stochastic approximation for robust speech recognition. IEEE Trans. on Speech and Audio Processing, vol. 11, no. 6, pp. 568-580 (2003)","DOI":"10.1109\/TSA.2003.818076"},{"key":"4_CR26","unstructured":"Li Deng, Jasha Droppo, and Alex Acero: Incremental Bayes Learning with Prior Evolution for Tracking Non-Stationary Noise Statistics from Noisy Speech Data. In: Proc. ICASSP, Hong Kong (2003)"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Li Deng, Jasha Droppo, and Alex Acero: Estimating cepstrum of speech under the presence of noise using a joint prior of static and dynamic features. IEEE Trans. on Speech and Audio Processing, vol. 12, no. 3, pp. 218-233 (2004)","DOI":"10.1109\/TSA.2003.822627"},{"key":"4_CR28","doi-asserted-by":"crossref","unstructured":"L. Deng, J. Droppo, and A. Acero: Dynamic compensation of HMM variances using the feature enhancement uncertainty computed from a parametric model of speech distortion. IEEE Trans. on Speech and Audio Processing, vol. 12, no. 3, (2005)","DOI":"10.1109\/TSA.2005.845814"},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"Li Deng, Mike Seltzer, Dong Yu, Alex Acero, A. Mohamed, and Geoff Hinton: Binary coding of speech spectrograms using a deep auto-encoder. In: Proc. Interspeech (2010)","DOI":"10.21437\/Interspeech.2010-487"},{"key":"4_CR30","unstructured":"J. Droppo, A. Acero, and L. Deng: Efficient online acoustic environment estimation for FCDCN in a continuous speech recognition system. In: Proc. ICASSP, Salt Lake City, Utah (2001)"},{"key":"4_CR31","doi-asserted-by":"crossref","unstructured":"J. Droppo, A. Acero, and L. Deng: A nonlinear observation model for removing noise from corrupted speech log Mel-spectral energies. In: Proc. ICSLP, Denver, Colorado (2002)","DOI":"10.21437\/ICSLP.2002-44"},{"key":"4_CR32","doi-asserted-by":"crossref","unstructured":"J. Droppo, A. Acero, and L. Deng: Uncertainty decoding with SPLICE for noise robust speech recognition. In: Proc. ICASSP, Orlando, Florida (2002)","DOI":"10.1109\/ICASSP.2002.1005674"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"J. Droppo, L. Deng, and A. Acero: Evaluation of SPLICE on the Aurora 2 and 3 Tasks. In: Proc. ICSLP, Denver, Colorado (2002)","DOI":"10.21437\/ICSLP.2002-6"},{"key":"4_CR34","doi-asserted-by":"crossref","unstructured":"J. Droppo and A. Acero: Environmental Robustness. In: Handbook of Speech Processing, Springer (2007)","DOI":"10.1007\/978-3-540-49127-9_33"},{"key":"4_CR35","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1109\/78.127947","volume":"40","author":"Y. Ephraim","year":"1992","unstructured":"Y. Ephraim: A Bayesian estimation approach for speech enhancement using hidden Markov models. IEEE Trans. on Acoustics, Speech, and Signal Processing, 40:725-735 (1992)","journal-title":"IEEE Trans. on Acoustics, Speech, and Signal Processing"},{"key":"4_CR36","doi-asserted-by":"crossref","unstructured":"Y. Ephraim and D. Malah: Speech enhancement using a minimum mean-square error short-time spectral amplitude estimator. IEEE Trans. Acoust., Speech, Signal Process., vol. ASSP-32, no. 6, pp. 1109-1121 (1984)","DOI":"10.1109\/TASSP.1984.1164453"},{"key":"4_CR37","doi-asserted-by":"crossref","unstructured":"B. Frey, L. Deng, A. Acero, and T.T. Kristjansson: Algonquin: Iterating Laplace\u2019s method to remove multiple types of acoustic distortion for robust speech recognition. In: Proc. Eurospeech, Aalborg, Denmark (2001)","DOI":"10.21437\/Eurospeech.2001-273"},{"key":"4_CR38","unstructured":"B. Frey, T. Kristjansson, Li Deng, and Alex Acero: Learning dynamic noise models from noisy speech for robust speech recognition. In: Proc. Advances in Neural Information Processing Systems (NIPS), vol. 14, Vancouver, Canada, 2001, pp. 101-108 (2001)"},{"key":"4_CR39","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1006\/csla.1995.0014","volume":"9","author":"MJF Gales","year":"1995","unstructured":"M.J.F. Gales and S.J. Young: Robust speech recognition in additive and convolutional noise using parallel model combination. Computer Speech and Language, 9:289-307 (1995)","journal-title":"Computer Speech and Language"},{"key":"4_CR40","doi-asserted-by":"crossref","unstructured":"M. J. F. Gales: Maximum Likelihood Linear Transformations For HMM-Based Speech Recognition. Computer Speech and Language, 12 (January 1998)","DOI":"10.1006\/csla.1998.0043"},{"key":"4_CR41","doi-asserted-by":"crossref","unstructured":"M.J.F. Gales: Model-based approaches to handling uncertainty. Chapter 5 of this book (2011)","DOI":"10.1007\/978-3-642-21317-5_5"},{"key":"4_CR42","doi-asserted-by":"publisher","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","volume":"18","author":"G Hinton","year":"2006","unstructured":"G. Hinton, S. Osindero, and Y. Teh: A fast learning algorithm for deep belief nets. Neural Computation, vol. 18, pp. 1527-1554, 2006)","journal-title":"Neural Computation"},{"key":"4_CR43","doi-asserted-by":"crossref","unstructured":"R. Haeb-Umbach and V. Ion: Soft features for improved distributed speech recognition over wireless networks. In: Proc. Interspeech (2004)","DOI":"10.21437\/Interspeech.2004-645"},{"key":"4_CR44","unstructured":"X. He, L. Deng, and W. Chou: Discriminative learning in sequential pattern recognition \u2014 A unifying review. IEEE Signal Processing Magazine (2008)"},{"key":"4_CR45","doi-asserted-by":"crossref","unstructured":"J. Hershey, S. Rennie, P. Olsen, and T. Kristjansson: Super-human multi-talker speech recognition: A graphical modeling approach. Computer Speech and Language (June 2010)","DOI":"10.1016\/j.csl.2008.11.001"},{"key":"4_CR46","unstructured":"H. G. Hirsch and D. Pearce: The Aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions. In: Proc. ISCA ITRW ASR (2000)"},{"issue":"6","key":"4_CR47","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1016\/j.specom.2008.02.002","volume":"50","author":"C Hsieh","year":"2008","unstructured":"C. Hsieh and C. Wu: Stochastic vector mapping-based feature enhancement using prior-models and model adaptation for noisy speech recognition. Speech Communication, vol. 50, No. 6, pp. 467-475 (2008)","journal-title":"Speech Communication"},{"key":"4_CR48","doi-asserted-by":"crossref","unstructured":"Y. Hu and Q. Huo: Irrelevant variability normalization based HMM training using VTS approximation of an explicit model of environmental distortions. In: Proc. Interspeech (2007)","DOI":"10.21437\/Interspeech.2007-99"},{"issue":"8","key":"4_CR49","doi-asserted-by":"publisher","first-page":"1241","DOI":"10.1109\/5.880082","volume":"88","author":"C-H Lee","year":"2000","unstructured":"C.-H. Lee and Q. Huo: On adaptive decision rules and decision parameter adaptation for automatic speech recognition. Proc. of the IEEE, vol. 88, No. 8, pp. 1241-1269 (2000)","journal-title":"Proc. of the IEEE"},{"key":"4_CR50","doi-asserted-by":"publisher","first-page":"1435","DOI":"10.1016\/j.specom.2006.03.007","volume":"48","author":"V Ion","year":"2006","unstructured":"V. Ion and R. Haeb-Umbach: Uncertainty decoding for distributed speech recognition over error-prone networks. Speech Communication, vol. 48, pp. 1435-1446 (2006)","journal-title":"Speech Communication"},{"issue":"5","key":"4_CR51","doi-asserted-by":"publisher","first-page":"1047","DOI":"10.1109\/TASL.2008.925879","volume":"16","author":"V Ion","year":"2008","unstructured":"V. Ion and R. Haeb-Umbach: A novel uncertainty decoding rule with applications to transmission error robust speech recognition. IEEE Trans. Speech and Audio Processing, vol. 16. No. 5, pp. 1047-1060 (2008)","journal-title":"IEEE Trans. Speech and Audio Processing"},{"issue":"8","key":"4_CR52","doi-asserted-by":"publisher","first-page":"874","DOI":"10.1109\/89.966090","volume":"9","author":"H Jiang","year":"2001","unstructured":"H. Jiang and Li Deng: A Bayesian approach to the verification problem: Applications to speaker verification. IEEE Trans. Speech and Audio Proc., vol. 9, No. 8, pp. 874-884 (2001)","journal-title":"IEEE Trans. Speech and Audio Proc."},{"issue":"1","key":"4_CR53","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1109\/89.979381","volume":"10","author":"H Jiang","year":"2002","unstructured":"H. Jiang and L. Deng: A robust compensation strategy against extraneous acoustic variations in spontaneous speech recognition. IEEE Trans. on Speech and Audio Processing, vol. 10, no. 1, pp. 9-17 (2002)","journal-title":"IEEE Trans. on Speech and Audio Processing"},{"key":"4_CR54","doi-asserted-by":"crossref","unstructured":"O. Kalinli, M.L. Seltzer, and A. Acero: Noise adaptive training using a vector Taylor series approach for noise robust automatic speech recognition. In: Proc. ICASSP, pages 3825-3828, Taipei, Taiwan (2009)","DOI":"10.1109\/ICASSP.2009.4960461"},{"key":"4_CR55","volume-title":"Noisy constrained maximum likelihood linear regression for noise robust speech recognition","author":"D Kim","year":"2010","unstructured":"D. Kim and M. Gales: Noisy constrained maximum likelihood linear regression for noise robust speech recognition. IEEE Trans. Audio Speech and Language Processing (2010)"},{"key":"4_CR56","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/S0167-6393(97)00061-7","volume":"24","author":"DY Kim","year":"1998","unstructured":"D.Y. Kim, C.K. Un, and N.S. Kim: Speech recognition in noisy environments using first-order vector Taylor series. Speech Communication, vol. 24, pp. 39-49 (1998)","journal-title":"Speech Communication"},{"key":"4_CR57","doi-asserted-by":"crossref","unstructured":"T.T. Kristjansson and B.J. Frey: Accounting for uncertainty in observations: A new paradigm for robust speech recognition. In: Proc. ICASSP, Orlando, Florida (2002)","DOI":"10.1109\/ICASSP.2002.5743654"},{"key":"4_CR58","unstructured":"T.T. Kristjansson, B. Frey, L. Deng, and A. Acero: Towards non-stationary model-based noise adaptation for large vocabulary speech recognition. In: Proc. ICASSP (2001)"},{"key":"4_CR59","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/S0167-6393(98)00028-4","volume":"25","author":"C-H Lee","year":"1998","unstructured":"C.-H. Lee: On stochastic feature and model compensation approaches to robust speech recognition. Speech Communication, vol. 25, pp. 29-47 (1998).","journal-title":"Speech Communication"},{"key":"4_CR60","doi-asserted-by":"crossref","unstructured":"V. Leutnant and R. Haeb-Umbach: An analytic derivation of a phase-sensitive observation model for noise robust speech recognition. In: Proc. Interspeech (2009)","DOI":"10.21437\/Interspeech.2009-367"},{"key":"4_CR61","doi-asserted-by":"crossref","unstructured":"J. Li, D. Yu, Y. Gong, and Li Deng: Unscented Transform with Online Distortion Estimation for HMM Adaptation. In: Proc. Interspeech (2010)","DOI":"10.21437\/Interspeech.2010-479"},{"key":"4_CR62","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1016\/j.csl.2009.02.001","volume":"23","author":"J Li","year":"2009","unstructured":"J. Li, D. Yu, L. Deng, Y. Gong, and A. Acero: A unified framework of HMM adaptation with joint compensation of additive and convolutive distortions. Computer Speech and Language, vol. 23, pp. 389-405 (2009)","journal-title":"Computer Speech and Language"},{"key":"4_CR63","unstructured":"J. Li, L. Deng, D. Yu, Y. Gong, and A. Acero: HMM Adaptation Using a Phase-Sensitive Acoustic Distortion Model for Environment-Robust Speech Recognition. In: Proc. ICASSP, Las Vegas (2008)"},{"key":"4_CR64","unstructured":"J. Li, L. Deng, D. Yu, J. Wu, Y. Gong, and A. Acero: Adaptation of compressed HMM parameters for resource-constrained speech recognition. In: Proc. ICASSP, Las Vegas (2008)"},{"key":"4_CR65","doi-asserted-by":"crossref","unstructured":"H. Liao and M. J. F. Gales: Issues with uncertainty decoding for noise robust speech recognition. In: Proc. ICSLP, pp. 1121-1124 (2006)","DOI":"10.21437\/Interspeech.2006-343"},{"key":"4_CR66","doi-asserted-by":"crossref","unstructured":"H. Liao and M. J. F. Gales: Adaptive training with joint uncertainty decoding for robust recognition of noisy data. In: Proc. ICASSP, vol. IV, pp. 389-392 (2007)","DOI":"10.1109\/ICASSP.2007.366931"},{"key":"4_CR67","doi-asserted-by":"crossref","unstructured":"H. Liao and M.J.F. Gales: Joint uncertainty decoding for noise robust speech recognition. In: Proc. Interspeech (2005)","DOI":"10.21437\/Interspeech.2005-265"},{"key":"4_CR68","doi-asserted-by":"crossref","unstructured":"Hui Lin, Li Deng, Dong Yu, Yifan Gong, Alex Acero, and Chi-Hui Lee: A study on multilingual acoustic modeling for large vocabulary ASR. In: Proc. ICASSP (2009)","DOI":"10.1109\/ICASSP.2009.4960588"},{"key":"4_CR69","doi-asserted-by":"crossref","unstructured":"R. Lyon: Machine hearing: An emerging field. IEEE Signal Processing Magazine (September 2010)","DOI":"10.1109\/MSP.2010.937498"},{"key":"4_CR70","doi-asserted-by":"crossref","unstructured":"A. Mohamed, D. Yu, and L. Deng: Investigation of full-sequence training of deep belief networks for speech recognition. In: Proc. Interspeech (2010)","DOI":"10.21437\/Interspeech.2010-304"},{"key":"4_CR71","unstructured":"P. Moreno: Speech Recognition in Noisy Environments. Ph.D. Thesis, Carnegie Mellon University (1996)"},{"issue":"5","key":"4_CR72","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1109\/MSP.2005.1511826","volume":"22","author":"N Morgan","year":"2005","unstructured":"N. Morgan et al.: Pushing the envelope \u2014 Aside. IEEE Signal Processing Magazine, vol. 22, No. 5, pp. 81-88 (2005)","journal-title":"IEEE Signal Processing Magazine"},{"issue":"3","key":"4_CR73","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1109\/MSP.2008.918418","volume":"25","author":"R Munkong","year":"2008","unstructured":"R. Munkong and B.-H. Juang: Auditory perception and cognition \u2014 Modularization and integration of signal processing from ears to brain. IEEE Signal Processing Magazine, vol. 25, No. 3, pp. 98-117 (2008)","journal-title":"IEEE Signal Processing Magazine"},{"key":"4_CR74","doi-asserted-by":"crossref","unstructured":"C. Rathinavalu and L. Deng: HMM-based speech recognition using state-dependent, discriminatively derived transforms on Mel-warped DFT features. IEEE Trans. on Speech and Audio Processing, pp. 243-256 (1997)","DOI":"10.1109\/89.568731"},{"key":"4_CR75","doi-asserted-by":"crossref","unstructured":"S. Rennie, J. Hershey, P. Olsen: Combining variational methods and loopy belief propagation for multi-talker speech recognition. IEEE Signal Processing Magazine, Special issue of Graphical Models for Signal Processing (Eds. M. Jordan et al.), (November 2010)","DOI":"10.21437\/Interspeech.2009-414"},{"issue":"5","key":"4_CR76","first-page":"445","volume":"6","author":"H Sameti","year":"1998","unstructured":"H. Sameti, H. Sheikhzadeh, Li Deng, and R. Brennan: HMM-based strategies for enhancement of speech signals embedded in nonstationary noise. IEEE Trans. on Speech and Audio Processing, vol. 6, no. 5, pp. 445-455 (1998)","journal-title":"Brennan: HMM-based strategies for enhancement of speech signals embedded in nonstationary noise. IEEE Trans. on Speech and Audio Processing"},{"key":"4_CR77","doi-asserted-by":"crossref","unstructured":"H. Sameti and Li Deng: Nonstationary-state hidden Markov model representation of speech signals for speech enhancement. Signal Processing, vol. 82, pp. 205-227 (2002)","DOI":"10.1016\/S0165-1684(01)00179-7"},{"key":"4_CR78","doi-asserted-by":"crossref","unstructured":"M. Seltzer, K. Kalgaonkar, and A. Acero: Acoustic model adaptation via linear spline interpolation for robust speech recognition. In: Proc. ICASSP (2010)","DOI":"10.1109\/ICASSP.2010.5495581"},{"issue":"1","key":"4_CR79","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1109\/89.260337","volume":"2","author":"H Sheikhzadeh","year":"1994","unstructured":"H. Sheikhzadeh and Li Deng: Waveform-based speech recognition using hidden filter models: Parameter selection and sensitivity to power normalization. IEEE Trans. on Speech and Audio Processing, vol. 2, no. 1, pp. 80-91 (1994)","journal-title":"IEEE Trans. on Speech and Audio Processing"},{"key":"4_CR80","doi-asserted-by":"crossref","unstructured":"G. Shi, Y. Shi, and Q. Huo: A study of irrelevant variability normalizataion based training and unsupervised online adaptation for LVCSR. In: Proc. Interspeech, Makuhari, Japan (2010)","DOI":"10.21437\/Interspeech.2010-20"},{"key":"4_CR81","doi-asserted-by":"crossref","unstructured":"V. Stouten,, H. Van hamme, P. Wambacq: Effect of phase-sensitive environment model and higher order VTS on noisy speech feature enhancement. In: Proc. ICASSP, pp. 433-436 (2005)","DOI":"10.1109\/ICASSP.2005.1415143"},{"key":"4_CR82","doi-asserted-by":"crossref","unstructured":"V. Stouten, H. Van hamme, and P. Wambacq: Accounting for the uncertainty of speech estimates in the context of model-based feature enhancement. In: Proc. ICSLP, pp. 105-108, Jeju Island, Korea (2004)","DOI":"10.21437\/Interspeech.2004-94"},{"key":"4_CR83","doi-asserted-by":"crossref","unstructured":"D. Yu, Li Deng, Yifan Gong, and Alex Acero: A novel framework and training algorithm for variable-parameter hidden Markov models. IEEE Trans. on Audio, Speech and Language Processing, vol. 17, no. 7, pp. 1348-1360, IEEE (2009)","DOI":"10.1109\/TASL.2009.2020890"},{"issue":"4","key":"4_CR84","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1109\/MSP.2009.932793","volume":"26","author":"D Yu","year":"2009","unstructured":"D. Yu and Li Deng: Solving nonlinear estimation problems using Splines. IEEE Signal Processing Magazine, vol. 26, no. 4, pp. 86-90, (2009)","journal-title":"IEEE Signal Processing Magazine"},{"key":"4_CR85","doi-asserted-by":"crossref","unstructured":"D. Yu, Li Deng, J. Droppo, J. Wu, Y. Gong, and A. Acero: Robust speech recognition using cepstral minimum-mean-square-error noise suppressor. IEEE Trans. Audio, Speech, and Language Processing, vol. 16, no. 5 (2008)","DOI":"10.1109\/TASL.2008.921761"},{"key":"4_CR86","doi-asserted-by":"crossref","unstructured":"D. Yu and L. Deng: Deep-Structured Hidden Conditional Random Fields for Phonetic Recognition. In: Proc. Interspeech (2010)","DOI":"10.21437\/Interspeech.2010-35"},{"key":"4_CR87","doi-asserted-by":"crossref","unstructured":"D. Zhu and Q. Huo: A maximum likelihood approach to unsupervised online adaptation of stochastic vector mapping function for robust speech recognition. In: Proc. ICASSP (2007)","DOI":"10.1109\/ICASSP.2007.367027"},{"key":"4_CR88","unstructured":"D. Zhu and Q. Huo: Irrelevant variability normalization based HMM training using MAP estimation of feature transforms for robust speech recognition. In: Proc. ICASSP (2008)"}],"container-title":["Robust Speech Recognition of Uncertain or Missing Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-21317-5_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T02:00:08Z","timestamp":1741312808000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-642-21317-5_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642213168","9783642213175"],"references-count":88,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-21317-5_4","relation":{},"subject":[],"published":{"date-parts":[[2011]]},"assertion":[{"value":"23 June 2011","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}