{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T15:28:07Z","timestamp":1760369287704},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2015,11,12]],"date-time":"2015-11-12T00:00:00Z","timestamp":1447286400000},"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\/s13634-015-0278-y","type":"journal-article","created":{"date-parts":[[2015,11,12]],"date-time":"2015-11-12T07:11:34Z","timestamp":1447312294000},"update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Environment-dependent denoising autoencoder for distant-talking speech recognition"],"prefix":"10.1186","volume":"2015","author":[{"given":"Yuma","family":"Ueda","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longbiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Atsuhiko","family":"Kai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,11,12]]},"reference":[{"issue":"6","key":"278_CR1","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1109\/MSP.2012.2205029","volume":"29","author":"T Yoshioka","year":"2012","unstructured":"T Yoshioka, A Sehr, M Delcroix, K Kinoshita, R Maas, T Nakatani, W Kellermann, Making machines understand us in reverberant rooms: robustness against reverberation for automatic speech recognition. IEEE Signal Process. Mag. 29(6), 114\u2013126 (2012).","journal-title":"IEEE Signal Process. Mag"},{"issue":"3","key":"278_CR2","first-page":"774","volume":"14","author":"M Wu","year":"2006","unstructured":"M Wu, D Wang, A two-stage algorithm for one-microphone reverberant speech enhancement. IEEE Trans. ASLP. 14(3), 774\u2013784 (2006).","journal-title":"IEEE Trans. ASLP"},{"issue":"7","key":"278_CR3","first-page":"2023","volume":"15","author":"Q Jin","year":"2007","unstructured":"Q Jin, T Schultz, A Waibel, Far-field speaker recognition. IEEE Trans. ASLP. 15(7), 2023\u20132032 (2007).","journal-title":"IEEE Trans. ASLP"},{"issue":"2","key":"278_CR4","first-page":"430","volume":"15","author":"M Delcroix","year":"2007","unstructured":"M Delcroix, T Hikichi, M Miyoshi, Precise dereverberation using multi-channel linear prediction. IEEE Trans. ASLP. 15(2), 430\u2013440 (2007).","journal-title":"IEEE Trans. ASLP"},{"key":"278_CR5","first-page":"173","volume-title":"Proc.of IEEE ICASSP","author":"EA Habets","year":"2005","unstructured":"EA Habets, in Proc.of IEEE ICASSP. Multi-channel speech dereverberation based on a statistical model of late reverberation (IEEEPennsylvania Convention Center, Philadelphia, Pennsylvania, USA, 2005), pp. 173\u2013176."},{"issue":"3","key":"278_CR6","first-page":"659","volume":"E94-D","author":"L Wang","year":"2011","unstructured":"L Wang, N Kitaoka, S Nakagawa, Distant-talking speech recognition based on spectral subtraction by multi-channel LMS algorithm.IEICE Trans. Inf. Syst.E94-D(3), 659\u2013667 (2011).","journal-title":"Inf. Syst."},{"issue":"12","key":"278_CR7","first-page":"1","volume":"2012","author":"L Wang","year":"2012","unstructured":"L Wang, K Odani, A Kai, Dereverberation and denoising based on generalized spectral subtraction by multi-channel LMS algorithm using a small-scale microphone array. Eurasip J. Adv. Signal Process. 2012(12), 1\u201311 (2012).","journal-title":"Eurasip J. Adv. Signal Process"},{"key":"278_CR8","first-page":"7117","volume-title":"Proc.of IEEE ICASSP","author":"W Li","year":"2013","unstructured":"W Li, L Wang, F Zhou, Q Liao, in Proc.of IEEE ICASSP. Joint sparse representation based cepstral-domain dereverberation for distant-talking speech recognition (IEEEVancouver Convention & Exhibition Center, Vancouver, BC, Canada, 2013), pp. 7117\u20137120."},{"issue":"3","key":"278_CR9","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1016\/j.specom.2007.09.004","volume":"50","author":"H Hirsch","year":"2008","unstructured":"H Hirsch, H Finster. Speech Comm.50(3), 244\u2013263 (2008).","journal-title":"Speech Comm."},{"issue":"7","key":"278_CR10","first-page":"1676","volume":"18","author":"A Sehr","year":"2010","unstructured":"A Sehr, R Maas, W Kellermann, Reverberation model-based decoding in the logmelspec domain for robust distant-talking speech recognition. IEEE Trans. ASLP. 18(7), 1676\u20131691 (2010).","journal-title":"IEEE Trans. ASLP"},{"key":"278_CR11","first-page":"5448","volume-title":"Proceedings of IEEE ICASSP","author":"SO Sadjadi","year":"2011","unstructured":"SO Sadjadi, JHL Hasnen, in Proceedings of IEEE ICASSP. Hilbert envelope based features for robust speaker identification under reverberant mismatched conditions (IEEEPrague, Czech Republic, 2011), pp. 5448\u20135451."},{"key":"278_CR12","first-page":"817","volume-title":"Proceedings of IEEE ICASSP 2006","author":"K Kinoshita","year":"2006","unstructured":"K Kinoshita, M Delcroix, T Nakatani, M Miyoshi, in Proceedings of IEEE ICASSP 2006. Spectral subtraction steered by multistep forward linear prediction for single channel speech dereverberation (IEEEToulouse, France, 2006), pp. 817\u2013820."},{"issue":"3","key":"278_CR13","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1587\/transinf.E94.D.659","volume":"E94-D","author":"L Wang","year":"2011","unstructured":"L Wang, N Kitaoka, S Nakagawa, Distant-talking speech recognition based on spectral subtraction by multi-channel LMS algorithm. IEICE Trans. Inf. Syst.E94-D(3), 659\u2013667 (2011).","journal-title":"IEICE Trans. Inf. Syst."},{"key":"278_CR14","first-page":"7224","volume-title":"Proc.of IEEE ICASSP 2013","author":"L Wang","year":"2013","unstructured":"L Wang, Z Zhang, A Kai, in Proc.of IEEE ICASSP 2013. Hands-free speaker identification based on spectral subtraction using a multi-channel least mean square approach (IEEEVancouver Convention & Exhibition Center, Vancouver, BC, Canada, 2013), pp. 7224\u20137228."},{"issue":"2","key":"278_CR15","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1109\/TASSP.1981.1163530","volume":"29","author":"S Furui","year":"1981","unstructured":"S Furui, Cepstral Analysis Technique for automatic speaker verification. IEEE Trans. Acoust. Speech Signal Process. 29(2), 254\u2013272 (1981).","journal-title":"IEEE Trans. Acoust. Speech Signal Process"},{"key":"278_CR16","unstructured":"F Liu, R Stern, X Huang, A Acero, in Proc.ARPA Speech Nat. Lang. Workshop. Efficient cepstral normalization for robust speech recognition, (1993), pp. 69\u201374."},{"key":"278_CR17","first-page":"817","volume-title":"Proc.of ICASSP","author":"L Wang","year":"2007","unstructured":"L Wang, N Kitaoka, S Nakagawa, in Proc.of ICASSP. Robust distant speech recognition by combining position-dependent CMN with conventional CMN (IEEEHonolulu, Hawaii, USA, 2007), pp. 817\u2013820."},{"issue":"2","key":"278_CR18","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1109\/TASSP.1979.1163209","volume":"27","author":"S Boll","year":"1979","unstructured":"S Boll, Suppression of acoustic noise in speech using spectral subtraction. IEEE Trans. Acoustics Speech Signal Process. 27(2), 113\u2013120 (1979).","journal-title":"IEEE Trans. Acoustics Speech Signal Process"},{"issue":"2","key":"278_CR19","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1109\/TASL.2008.2009161","volume":"17","author":"M Wolfel","year":"2009","unstructured":"M Wolfel, Enhanced speech features by single-channel joint compensation of noise and reverberation. IEEE Trans. Audio Speech Lang. Process. 17(2), 312\u2013323 (2009).","journal-title":"IEEE Trans. Audio Speech Lang. Process"},{"key":"278_CR20","unstructured":"Y Konig, L Heck, M Weintraub, K Sonmez, in Proc.of RLA2C, ESCA workshop on Speaker Recognition and its Commercial and Forensic Applications. Nonlinear discriminant feature extraction for robust text-independent speaker recognition (ESCA, 1998), pp. 72\u201375."},{"key":"278_CR21","unstructured":"Q Zhu, A Stolcke, B-Y Chen, N Morgan, in Proc.of INTERSPEECH 2005. Using MLP features in SRI\u2019s conversational speech recognition system, (2005), pp. 2141\u20132144."},{"issue":"5786","key":"278_CR22","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"G Hinton","year":"2006","unstructured":"G Hinton, R Salakhutdinov, Reducing the dimensionality of data with neural networks. Science.313(5786), 504\u2013507 (2006).","journal-title":"Science."},{"issue":"1","key":"278_CR23","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1109\/LSP.2013.2291240","volume":"21","author":"Y Xu","year":"2014","unstructured":"Y Xu, J Du, L-R Dai, C-H Lee, An experimental study on speech enhancement based on deep neural net-works. IEEE Signal Proc. Lett. 21(1), 65\u201368 (2014).","journal-title":"IEEE Signal Proc. Lett"},{"key":"278_CR24","unstructured":"F-J Weninger, S Watanabe, J-L Roux, J Hershey, Y Tachioka, J-T Geiger, G Rigoll, B-W Schuller, The MERL\/MELCO\/TUM system for the REVERB Challenge using Deep Recurrent Neural Network Feature Enhancement, (Florence, Italy, 2014)."},{"issue":"4","key":"278_CR25","doi-asserted-by":"publisher","first-page":"888","DOI":"10.1016\/j.csl.2014.01.001","volume":"28","author":"F Weninger","year":"2014","unstructured":"F Weninger, J Geiger, M Wollmer, B Schuller, G Rigoll, Feature enhancement by deep LSTM networks for ASR in reverberant multisource environments. Comput. Speech Lang. 28(4), 888\u2013902 (2014).","journal-title":"Comput. Speech Lang"},{"key":"278_CR26","first-page":"4623","volume-title":"Proc.of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"F Weninger","year":"2014","unstructured":"F Weninger, S Watanabe, Y Tachioka, B Schuller, in Proc.of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Deep recurrent de-noising auto-encoder and blind de-reverberation for reverberated speech recognition (IEEEFlorence, Italy, 2014), pp. 4623\u20134627."},{"key":"278_CR27","unstructured":"X Xiao, S Zhao, DHH Nguyen, X Zhong, D-L Jones, ES Chng, H Li, in proceedings of Reverberation Challenge Workshop. The NTU-ADSC systems for Reverberation Challenge 2014 (Florence, Italy, 2014)."},{"key":"278_CR28","first-page":"4356","volume-title":"Proc.of ICASSP","author":"M Mimura","year":"2015","unstructured":"M Mimura, S Sakai, T Kawahara, in Proc.of ICASSP. Deep autoencoders augmented with phone-class feature for reverberant speech recognition (IEEEBrisbane, Queensland, Australia, 2015), pp. 4356\u20134369."},{"key":"278_CR29","first-page":"116","volume-title":"Proceedings of ICASSP","author":"S Araki","year":"2015","unstructured":"S Araki, T Hayashi, M Delcroix, M Fujimoto, K Takeda, T Nakatani, in Proceedings of ICASSP. Exploring multi-channel features for denoising-autoencoder-based speech enhancement (IEEEBrisbane, Queensland, Australia, 2015), pp. 116\u2013120."},{"key":"278_CR30","first-page":"3371","volume":"11","author":"P Vincent","year":"2010","unstructured":"P Vincent, H Larochelle, I Lajoie, Y Bengio, PA Manzagol, Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11:, 3371\u20133408 (2010).","journal-title":"J. Mach. Learn. Res"},{"key":"278_CR31","first-page":"436","volume-title":"Proc.Interspeech","author":"X Lu","year":"2013","unstructured":"X Lu, Y Tsao, S Matsuda, C Hori, in Proc.Interspeech. Speech enhancement based on deep denoising autoencoder (ISCALyon, France, 2013), pp. 436\u2013440."},{"key":"278_CR32","first-page":"1759","volume-title":"Proc.of ICASSP 2014","author":"X Feng","year":"2014","unstructured":"X Feng, Y Zhang, JR Glass, in Proc.of ICASSP 2014. Speech feature denising and dereverberation via deep autoencoder for noisy reverberant speech recognition (IEEEFlorence, Italy, 2014), pp. 1759\u20131763."},{"key":"278_CR33","doi-asserted-by":"crossref","first-page":"885","DOI":"10.21437\/Interspeech.2014-222","volume-title":"Proc.of INTERSPEECH 2014","author":"X Lu","year":"2014","unstructured":"X Lu, Y Tsao, S Matsuda, C Hori, in Proc.of INTERSPEECH 2014. Ensemble modeling of denoising autoencoder for speech spectrum restoration (ISCASingapore, 2014), pp. 885\u2013889."},{"key":"278_CR34","first-page":"3512","volume-title":"Proc.Interspeech","author":"T Ishii","year":"2013","unstructured":"T Ishii, H Komiyama, T Shinozaki, Y Horiuchi, S Kuroiwa, in Proc.Interspeech. Reverberant speech recognition based on denoising autoencoder (ISCALyon, France, 2013), pp. 3512\u20133516."},{"key":"278_CR35","first-page":"379","volume-title":"Proc.of International Symposium on Chinese Spoken Language Processing 2014","author":"Y Ueda","year":"2014","unstructured":"Y Ueda, L Wang, A Kai, X Xiao, E Chng, H Li, in Proc.of International Symposium on Chinese Spoken Language Processing 2014. Single-channel dereverberation for distant-talking speech recognition by combining denoising autoencoder and temporal structure normalization (IEEESingapore, 2014), pp. 379\u2013383."},{"key":"278_CR36","first-page":"7398","volume-title":"Proceedings of ICASSP","author":"ML Seltzer","year":"2013","unstructured":"ML Seltzer, D Yu, Y Wang, in Proceedings of ICASSP. An investigation of deep neural networks for noise robust speech recognition (IEEEVancouver Convention & Exhibition Center, Vancouver, BC, Canada, 2013), pp. 7398\u20137402."},{"key":"278_CR37","first-page":"5014","volume-title":"Proceedings of ICASSP","author":"R Giri","year":"2015","unstructured":"R Giri, ML Seltzer, J Droppo, D Yu, in Proceedings of ICASSP. Improving speech recognition in reverberation using a room-aware deep neural network and multi-task learning (IEEEBrisbane, Queensland, Australia, 2015), pp. 5014\u20135018."},{"key":"278_CR38","first-page":"55","volume-title":"Proceedings of Automatic Speech Recognition and Understanding (ASRU)","author":"G Saon","year":"2013","unstructured":"G Saon, H Soltau, D Nahamoo, M Picheny, in Proceedings of Automatic Speech Recognition and Understanding (ASRU). Speaker adaptation of neural network acoustic models using i-vectors (IEEEOlomouc, Czech Republic, 2013), pp. 55\u201359."},{"issue":"4","key":"278_CR39","first-page":"337","volume":"21","author":"XL Zhang","year":"2013","unstructured":"XL Zhang, J Wu, Deep belief networks based voice activity detection. IEEE Trans. Audio, Speech, Lang. Process. 21(4), 337\u20133408 (2013).","journal-title":"IEEE Trans. Audio, Speech, Lang. Process"},{"key":"278_CR40","volume-title":"Proceedings of the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA-13)","author":"K Kinoshita","year":"2013","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 (IEEEMohonk Mountain House in New Paltz, New York, USA, 2013)."},{"key":"278_CR41","first-page":"81","volume-title":"Proc.ICASSP 95","author":"T Robinson","year":"1995","unstructured":"T Robinson, J Fransen, D Pye, J Foote, S Renals, in Proc.ICASSP 95. Wsjcam0: A British English speech corpus for large vocabulary continuous speech recognition (IEEEDetroit, Michigan, USA, 1995), pp. 81\u201384."},{"key":"278_CR42","unstructured":"M Lincoln, I McCowan, I Vepa, HK Maganti, in Proc.ASRU. The multi-channel wall street journal audio visual corpus (MC-WSJ-AV): specification and initial experiments, (2005), pp. 357\u2013362."},{"issue":"2","key":"278_CR43","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1016\/j.csl.2010.06.003","volume":"25","author":"D Povey","year":"2011","unstructured":"D Povey, L Burget, et al., The subspace Gaussian mixture model\u2014a structured model for speech recognition. Comput. Speech Lang. 25(2), 404\u2013439 (2011).","journal-title":"Comput. Speech Lang"},{"key":"278_CR44","first-page":"1","volume-title":"Proc.of IEEE 2011 workshop on, Automatic Speech Recognition and Understanding","author":"D Povey","year":"2011","unstructured":"D Povey, A Ghoshal, G Boulianne, L Burget, O Glembek, N Goel, M Hannemann, P Motlicek, Y Qian, P Schwarz, J Silovsky, G Stemmer, K Vesely, in Proc.of IEEE 2011 workshop on, Automatic Speech Recognition and Understanding. The Kaldi speech recognition toolkit (IEEEHawaii, USA, 2011), pp. 1\u20134."},{"key":"278_CR45","unstructured":"J Alam, V Gupta, P Kenny, P Dumouchel, in Proc.of REVERB Workshop. Use of multiple front-ends and i-vector-based speaker adaptation for robust speech recognition (Florence, Italy, 2014)."},{"key":"278_CR46","unstructured":"Y Tachioka, T Narita, FJ Weninger, S Watanabe, in Proc.of REVERB Workshop. Dual system combination approach for various reverberant environments with dereverberation techniques (Florence, Italy, 2014)."}],"container-title":["EURASIP Journal on Advances in Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13634-015-0278-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s13634-015-0278-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13634-015-0278-y","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13634-015-0278-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,25]],"date-time":"2022-05-25T23:27:27Z","timestamp":1653521247000},"score":1,"resource":{"primary":{"URL":"https:\/\/asp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13634-015-0278-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,11,12]]},"references-count":46,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2015,12]]}},"alternative-id":["278"],"URL":"https:\/\/doi.org\/10.1186\/s13634-015-0278-y","relation":{},"ISSN":["1687-6180"],"issn-type":[{"value":"1687-6180","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,11,12]]},"article-number":"92"}}