{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T18:03:00Z","timestamp":1772301780274,"version":"3.50.1"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2015,7,23]],"date-time":"2015-07-23T00:00:00Z","timestamp":1437609600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["EURASIP J. Adv. Signal Process."],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1186\/s13634-015-0246-6","type":"journal-article","created":{"date-parts":[[2015,7,22]],"date-time":"2015-07-22T18:59:55Z","timestamp":1437591595000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Reverberant speech recognition combining deep neural networks and deep autoencoders augmented with a phone-class feature"],"prefix":"10.1186","volume":"2015","author":[{"given":"Masato","family":"Mimura","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinsuke","family":"Sakai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatsuya","family":"Kawahara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,7,23]]},"reference":[{"key":"246_CR1","doi-asserted-by":"crossref","unstructured":"AE Rosenberg, CH Lee, FK Soong, in ICSLP. Cepstral channel normalization techniques for HMM-based speaker verification (ISCA,Yokohama, Japan, 1994), pp. 1835\u20131838.","DOI":"10.21437\/ICSLP.1994-461"},{"key":"246_CR2","doi-asserted-by":"crossref","unstructured":"CJ Leggetter, PC Woodland, in Computer Speech and Lang, 9. Maximum likelihood linear regression for speaker adaptation of continuous density hidden markov models (Academic Press Inc, 1995), pp. 171\u2013185.","DOI":"10.1006\/csla.1995.0010"},{"issue":"1","key":"246_CR3","first-page":"134","volume":"43","author":"M Gurelli","year":"1995","unstructured":"M Gurelli, C Nikias, Evam: An eigenvector-based algorithm for multichannel blind deconvolution of input colored signals. IEEE Trans. Audio, Speech Lang. Process. 43(1), 134\u2013149 (1995).","journal-title":"IEEE Trans. Audio, Speech Lang. Process"},{"key":"246_CR4","doi-asserted-by":"crossref","unstructured":"M Delcroix, T Hikichi, M Miyoshi, in ICASSP, 1. On the use of lime dereverberation algorithm in an acoustic environment with a noise source (IEEE,Toulouse, France, 2006).","DOI":"10.1109\/ICASSP.2006.1660148"},{"key":"246_CR5","doi-asserted-by":"crossref","unstructured":"S Gannot, M Moonen, in EURASIP J. Appl. Signal Process, 11. Subspace methods for multimicrophone speech dereverberation (Springer, 2003), pp. 1074\u20131090.","DOI":"10.1155\/S1110865703305049"},{"issue":"3","key":"246_CR6","doi-asserted-by":"publisher","first-page":"774","DOI":"10.1109\/TSA.2005.858066","volume":"14","author":"M Wu","year":"2006","unstructured":"M Wu, D Wang, A two-stage algorithm for one-microphone reverberant speech enhancement. IEEE Trans. Audio Speech Lang. Process. 14(3), 774\u2013784 (2006).","journal-title":"IEEE Trans. Audio Speech Lang. Process"},{"issue":"4","key":"246_CR7","doi-asserted-by":"publisher","first-page":"534","DOI":"10.1109\/TASL.2008.2009015","volume":"17","author":"K Kinoshita","year":"2009","unstructured":"K Kinoshita, M Delcroix, T Nakatani, M Miyoshi, Suppression of late reverberation effect on speech signal using long-term multiplestep linear prediction. IEEE Trans. Audio, Speech Lang. Process. 17(4), 534\u2013545 (2009).","journal-title":"IEEE Trans. Audio, Speech Lang. Process"},{"issue":"7","key":"246_CR8","doi-asserted-by":"publisher","first-page":"1708","DOI":"10.1109\/TASL.2010.2052610","volume":"18","author":"R Gomez","year":"2010","unstructured":"R Gomez, T Kawahara, Robust speech recognition based on dereverberation parameter optimization using acoustic model likelihood. IEEE Trans. Audio Speech Lang. Process. 18(7), 1708\u20131716 (2010).","journal-title":"IEEE Trans. Audio Speech Lang. Process"},{"key":"246_CR9","doi-asserted-by":"crossref","unstructured":"L Deng, M Seltzer, D Yu, A Acero, A-r Mohamed, G Hinton, in INTERSPEECH. Binary coding of speech spectrograms using a deep auto-encoder (ISCA,Makuhari, Japan, 2010), pp. 1692\u20131695.","DOI":"10.21437\/Interspeech.2010-487"},{"key":"246_CR10","doi-asserted-by":"crossref","unstructured":"T Ishii, H Komiyama, T Shinozaki, Y Horiuchi, S Kuroiwa, in INTERSPEECH. Reverberant speech recognition based on denoising autoencoder (ISCA,Lyon, France, 2013), pp. 3512\u20133516.","DOI":"10.21437\/Interspeech.2013-267"},{"key":"246_CR11","doi-asserted-by":"crossref","unstructured":"X Feng, Y Zhang, J Glass, in Proc. ICASSP. Speech feature denoising and dereverberation via deep autoencoders for noisy reverberant speech recognition (IEEE,Florence, Italy, 2014), pp. 1778\u20131782.","DOI":"10.1109\/ICASSP.2014.6853900"},{"key":"246_CR12","doi-asserted-by":"crossref","unstructured":"F Weninger, S Watanabe, Y Tachioka, B Schuller, in Proc. ICASSP. Deep reccurent de-noising auto-encoder and blind de-reverberation for reverberated speech recognition (IEEE,Florence, Italy, 2014), pp. 4656\u20134660.","DOI":"10.1109\/ICASSP.2014.6854478"},{"key":"246_CR13","doi-asserted-by":"crossref","unstructured":"M Mimura, S Sakai, T Kawahara, in HSCMA,. Exploiting deep neural networks and deep autoencoders in reverberant speech recognition (IEEE,Nancy, France, 2014).","DOI":"10.1109\/HSCMA.2014.6843279"},{"issue":"1","key":"246_CR14","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/TASL.2011.2134090","volume":"20","author":"GE Dahl","year":"2012","unstructured":"GE Dahl, D Yu, L Deng, A Acero, Context-dependent pre-trained deep neural networks for large vocabulary speech recognition. IEEE Trans. Audio Speech Lang. Proc. 20(1), 30\u201342 (2012).","journal-title":"IEEE Trans. Audio Speech Lang. Proc"},{"key":"246_CR15","doi-asserted-by":"crossref","unstructured":"X Lu, Y Tsao, S Matsuda, C Hori, in INTERSPEECH. Speech enhancement based on deep denoising autoencoder (ISCA,Lyon, France, 2013), pp. 436\u2013440.","DOI":"10.21437\/Interspeech.2013-130"},{"key":"246_CR16","doi-asserted-by":"crossref","unstructured":"CM Bishop, Neural networks for pattern recognition (Oxford University Press, Oxford, 1995).","DOI":"10.1201\/9781420050646.ptb6"},{"key":"246_CR17","doi-asserted-by":"publisher","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","volume":"18","author":"GE Hinton","year":"2006","unstructured":"GE Hinton, S Osindero, Y Teh, A fast learning algorithm for deep belief nets. Neural Comput. 18, 1527\u20131554 (2006).","journal-title":"Neural Comput"},{"issue":"6","key":"246_CR18","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"GE Hinton","year":"2012","unstructured":"GE Hinton, L Deng, D Yu, G Dahl, A Mohamed, N Jaitly, A Senior, V Vanhoucke, P Nguyen, T Sainath, B Kingsbury, Deep neural networks for acoustic modeling in speech recognition. IEEE Signal Process. Mag. 29(6), 82\u201397 (2012).","journal-title":"IEEE Signal Process. Mag"},{"issue":"1","key":"246_CR19","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/TASL.2011.2109382","volume":"20","author":"A Mohamed","year":"2012","unstructured":"A Mohamed, G Dahl, G Hinton, Acoustic modelling using deep belief networks. IEEE Trans. Audio Speech Lang. Proc. 20(1), 14\u201322 (2012).","journal-title":"IEEE Trans. Audio Speech Lang. Proc"},{"key":"246_CR20","doi-asserted-by":"crossref","unstructured":"F Seide, G Li, D Yu, in INTERSPEECH. Conversational speech transcription using context-dependent deep neural networks (ISCA,Florence, Italy, 2011), pp. 437\u2013440.","DOI":"10.21437\/Interspeech.2011-169"},{"issue":"1","key":"246_CR21","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1109\/TASL.2011.2116010","volume":"20","author":"N Morgan","year":"2012","unstructured":"N Morgan, Deep and wide: Multiple layers in automatic speech recognition. IEEE Trans. Audio Speech Lang. Proc. 20(1), 7\u201313 (2012).","journal-title":"IEEE Trans. Audio Speech Lang. Proc"},{"issue":"1","key":"246_CR22","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1109\/TASL.2011.2129510","volume":"20","author":"GSVS Sivaram","year":"2012","unstructured":"GSVS Sivaram, H Hermansky, Sparse multilayer perceptron for phoneme recognition. IEEE Trans. Audio Speech Lang. Proc. 20(1), 23\u201329 (2012).","journal-title":"IEEE Trans. Audio Speech Lang. Proc"},{"key":"246_CR23","doi-asserted-by":"crossref","unstructured":"PJ Bell, MJF Gales, P Lanchantin, X Liu, Y Long, S Renals, P Swietojanski, PC Woodland, in Proc. SLT. Transcriptions of multi-genre media archives using out-of-domain data (IEEE,Miami, USA, 2012), pp. 324\u2013329.","DOI":"10.1109\/SLT.2012.6424244"},{"key":"246_CR24","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"GE Hinton","year":"2006","unstructured":"GE Hinton, RR Salakhutdinov, Reducing the dimensionality of data with neural networks. Science. 313, 504\u2013507 (2006).","journal-title":"Science"},{"key":"246_CR25","doi-asserted-by":"crossref","unstructured":"Y Bengio, P Lamblin, D Popovici, H Larochelle, in Advances in Neural Information Processing Systems 19 (NIPS06). Greedy layer-wise training of deep networks (MIT Press, 2007), pp. 153\u2013160.","DOI":"10.7551\/mitpress\/7503.003.0024"},{"key":"246_CR26","doi-asserted-by":"crossref","unstructured":"P Vincent, H Larochelle, Y Bengio, PA Manzagol, in Proceedings of the Twenty-fifth International Conference on Machine Learning (ICML\u201808). Extracting and composing robust features with denoising autoencoders (ACMHelsinki, Finland, 2008), pp. 1096\u20131103.","DOI":"10.1145\/1390156.1390294"},{"key":"246_CR27","doi-asserted-by":"crossref","unstructured":"J Du, Q Wang, T Gao, Y Xu, L Dai, C-H Lee, in INTERSPEECH. Robust speech recognition with speech enhanced deep neural networks (ISCA,Singapore, 2014), pp. 616\u2013620.","DOI":"10.21437\/Interspeech.2014-148"},{"key":"246_CR28","doi-asserted-by":"crossref","unstructured":"G Saon, H Soltau, D Nahamoo, M Picheny, in Proc. ASRU. Speaker adaptation of neural network acoustic models using I-Vevtors (IEEE,Olomouc, Czech, 2013), pp. 55\u201359.","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"246_CR29","doi-asserted-by":"crossref","unstructured":"P Karanasou, Y Wang, MJF Gales, PC Woodland, in INTERSPEECH. Adaptation of deep neural network acoustic models using factorised i-vectors (ISCA,Singapore, 2014), pp. 616\u2013620.","DOI":"10.21437\/Interspeech.2014-488"},{"key":"246_CR30","doi-asserted-by":"crossref","unstructured":"M Seltzer, D Yu, Y Wang, in Proc. ICASSP. An Investigation of deep neural networks for noise robust speech recognition (IEEE,Vancouver, Canada, 2013), pp. 7398\u20137402.","DOI":"10.1109\/ICASSP.2013.6639100"},{"issue":"3","key":"246_CR31","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1109\/89.496215","volume":"4","author":"A Sankar","year":"1996","unstructured":"A Sankar, C-H Lee, A maximum-likelihood approach to stochastic matching for robust speech recognition. IEEE Trans. Speech Audio Process. 4(3), 190\u2013202 (1996).","journal-title":"IEEE Trans. Speech Audio Process"},{"key":"246_CR32","doi-asserted-by":"crossref","unstructured":"K Kinoshita, M Delcroix, T Yoshioka, T Nakatani, E Habets, R Haeb-Umbach, V Leutnant, A Sehr, W Kellermann, R Maas, S Gannot, B Raj, in Proceedings of the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA-13). The reverb challenge: a common evaluation framework for dereverberation and recognition of reverberant speech (IEEE,New York, USA, 2013).","DOI":"10.1109\/WASPAA.2013.6701894"},{"key":"246_CR33","unstructured":"V Mnih, in Department of Computer Science, University of Toronto, Tech. Rep. UTML TR. Cudamat: a CUDA-based matrix class for python (University of Toronto, 2009)."}],"container-title":["EURASIP Journal on Advances in Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s13634-015-0246-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13634-015-0246-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13634-015-0246-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13634-015-0246-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T15:44:01Z","timestamp":1748533441000},"score":1,"resource":{"primary":{"URL":"https:\/\/asp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13634-015-0246-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,7,23]]},"references-count":33,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2015,12]]}},"alternative-id":["246"],"URL":"https:\/\/doi.org\/10.1186\/s13634-015-0246-6","relation":{},"ISSN":["1687-6180"],"issn-type":[{"value":"1687-6180","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,7,23]]},"assertion":[{"value":"17 February 2015","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 July 2015","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 July 2015","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"62"}}