{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T11:58:56Z","timestamp":1774871936187,"version":"3.50.1"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2015,6,19]],"date-time":"2015-06-19T00:00:00Z","timestamp":1434672000000},"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\/s13634-015-0238-6","type":"journal-article","created":{"date-parts":[[2015,6,18]],"date-time":"2015-06-18T10:32:22Z","timestamp":1434623542000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Speech recognition in reverberant and noisy environments employing multiple feature extractors and i-vector speaker adaptation"],"prefix":"10.1186","volume":"2015","author":[{"given":"Md Jahangir","family":"Alam","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vishwa","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrick","family":"Kenny","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pierre","family":"Dumouchel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,6,19]]},"reference":[{"key":"238_CR1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-84996-056-4","volume-title":"Speech Dereverberation, Signals and Communication Technology Series","author":"PA Naylor","year":"2010","unstructured":"PA Naylor, ND Gaubitch, Speech Dereverberation, Signals and Communication Technology Series, 2010th edn. (Springer-Verlag, London, 2010)","edition":"2010"},{"key":"238_CR2","doi-asserted-by":"crossref","unstructured":"Kumar K, Stern RM, Maximum-likelihood-based cepstral inverse filtering for blind speech dereverberation, in Proc. of ICASSP (Dallas, Texas, 2010)","DOI":"10.1109\/ICASSP.2010.5495667"},{"key":"238_CR3","unstructured":"Alam MJ, Gupta V, Kenny P, Dumouchel P, Use of multiple front-ends and i-vector based speaker adaptation for robust speech recognition, in Proc. of REVERB Challenge (Florence, Italy, 2014)"},{"key":"238_CR4","unstructured":"MJ Alam, P Kenny, P Dumouchel, D O\u2019Shaughnessy, Robust feature extractors for continuous speech recognition, in Proc. of EUSIPCO (Lisbon, Portugal, 2014)"},{"key":"238_CR5","doi-asserted-by":"crossref","unstructured":"A Schwarz, C Heummer, R Maas, W Kellermann, Spatial diffuseness features for DNN-based speech recognition in noisy and reverberant environments, in Proc. of ICASSP (Brisbane, Australia 2015)","DOI":"10.1109\/ICASSP.2015.7178798"},{"key":"238_CR6","doi-asserted-by":"crossref","unstructured":"L Deng, J Li, J-T Huang, K Yao, D Yu, F Seide, M Seltzer, G Zweig, X He, J Williams, Y Gong, A Acero, Recent advances in deep learning for speech research at Microsoft, in Proc. Int. Conf. Acoust., Speech, Signal Process (Vancouver, Canada, 2013) p. 8604\u20138608","DOI":"10.1109\/ICASSP.2013.6639345"},{"key":"238_CR7","unstructured":"A-R Mohamed, G Hinton, G Penn, Understanding how deep belief networks perform acoustic modelling, in Proc. Int. Conf. Acoust., Speech, Signal Process, (2012) p. 4273\u20134276"},{"key":"238_CR8","doi-asserted-by":"crossref","unstructured":"T Yoshioka, A Ragni, MJF Gales, Investigation of unsupervised adaptation of DNN acoustic models with filter bank input, in Proceed. of ICASSP (Florence, Italy, 2014) p. 6344\u20136348. online: http:\/\/mi.eng.cam.ac.uk\/~mjfg\/yoshioka_ICASSP14.pdf","DOI":"10.1109\/ICASSP.2014.6854825"},{"issue":"1","key":"238_CR9","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 modeling using deep belief networks. IEEE. Trans. Audio. Speech. Lang. Process. 20(1), 14\u201322 (2012)","journal-title":"IEEE. Trans. Audio. Speech. Lang. Process."},{"issue":"1","key":"238_CR10","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/TASL.2011.2134090","volume":"20","author":"G Dahl","year":"2012","unstructured":"G Dahl, D Yu, L Deng, A Acero, Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE. Trans. Audio. Speech. Lang. Process. 20(1), 30\u201342 (2012)","journal-title":"IEEE. Trans. Audio. Speech. Lang. Process."},{"key":"238_CR11","doi-asserted-by":"crossref","unstructured":"JG Fiscus, A post-processing system to yield reduced error word rates: recognizer output voting error reduction (ROVER), in IEEE Workshop on Automatic Speech Recognition and Understanding (Santa Barbara, CA, 1997) p. 347\u2013354","DOI":"10.1109\/ASRU.1997.659110"},{"key":"238_CR12","unstructured":"Y Tachioka, T Narita, FJ Weninger, S Watanabe, Dual system combination approach for various reverberant environments with dereverberation techniques, in Proceed. of REVERB Challenge Workshop (Florence, Italy, 2014). online: http:\/\/reverb2014.dereverberation.com\/workshop\/reverb2014-papers\/1569886337.pdf"},{"key":"238_CR13","doi-asserted-by":"crossref","unstructured":"V Gupta, P Kenny, P Ouellet, T Stafylakis, I-vector-based speaker adaptation of deep neural networks for French broadcast audio transcription, in Proc. of ICASSP (Florence, Italy, 2014)","DOI":"10.1109\/ICASSP.2014.6854823"},{"issue":"2","key":"238_CR14","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1016\/j.specom.2012.08.007","volume":"55","author":"MJ Alam","year":"2013","unstructured":"MJ Alam, T Kinnunen, P Kenny, P Ouellet, D O\u2019Shaughnessy, Multitaper MFCC and PLP features for speaker verification using i-vectors. Speech Comm. 55(2), 237\u2013251 (2013)","journal-title":"Speech Comm."},{"issue":"4","key":"238_CR15","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1007\/s12559-012-9197-5","volume":"5","author":"MJ Alam","year":"2012","unstructured":"MJ Alam, P Kenny, D O\u2019Shaughnessy, Low-variance multi-taper mel-frequency cepstral coefficient features for speech and speaker recognition systems. Springer Cognit. Comput. J. 5(4), 533\u2013544 (2012)","journal-title":"Springer Cognit. Comput. J."},{"key":"238_CR16","doi-asserted-by":"crossref","unstructured":"S Dharanipragada, BD Rao, MVDR based feature extraction for robust speech recognition, in Proc. of ICASSP (Salt Lake Ciy, Utah, 2001) p. 309\u2013312","DOI":"10.1109\/ICASSP.2001.940829"},{"key":"238_CR17","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1002\/j.1538-7305.1961.tb03976.x","volume":"40","author":"D Slepian","year":"1960","unstructured":"D Slepian, HO Pollak, Prolate spheroidal wave functions, Fourier analysis and uncertainty - I. Bell. Syst. Tech. J. 40, 43\u201363 (1960)","journal-title":"Syst. Tech. J."},{"issue":"9","key":"238_CR18","doi-asserted-by":"publisher","first-page":"1055","DOI":"10.1109\/PROC.1982.12433","volume":"70","author":"DJ Thomson","year":"1982","unstructured":"DJ Thomson, Spectrum estimation and harmonic analysis. Proc. IEEE. 70(9), 1055\u20131096 (1982)","journal-title":"Proc. IEEE."},{"key":"238_CR19","doi-asserted-by":"crossref","unstructured":"Alam J, Ouellet P, Kenny P, O\u2019Shaughnessy D, Comparative evaluation of feature normalization techniques for speaker verification, in Proc of NOLISP, LNAI 7015, 246\u2013253 (Las Palmas, Spain, 2011)","DOI":"10.1007\/978-3-642-25020-0_32"},{"key":"238_CR20","unstructured":"D Povey, A Ghoshal, G Boulianne, L Burget, O Glembek, N Goel, M Hanneman, P Motlicek, Y Qian, P Schwarz, J Silovsky, G Stemmer, K Vesely, The Kaldi speech recognition toolkit, in Proc. of ASRU (Hawaii, 2011)"},{"key":"238_CR21","doi-asserted-by":"crossref","unstructured":"MJ Alam, P Kenny, D O\u2019Shaughnessy, Robust feature extraction for speech recognition by enhancing auditory spectrum, in Proc. of Interspeech (Portland, Oregon, 2012)","DOI":"10.21437\/Interspeech.2012-392"},{"key":"238_CR22","unstructured":"MJ Alam, P Kenny, D O\u2019Shaughnessy, Robust feature extraction based on an asymmetric level-dependent auditory filterbank and a subband spectrum enhancement technique, in Digital Signal Processing, 29 (2014) p. 147\u2013157"},{"key":"238_CR23","doi-asserted-by":"crossref","unstructured":"Timo Gerkmann, Richard C. Hendrikes, Noise power estimation based on the probability of speech presence, in Proc. IEEE WASPAA (New York, 2011) p. 145\u2013148","DOI":"10.1109\/ASPAA.2011.6082266"},{"key":"238_CR24","doi-asserted-by":"crossref","unstructured":"RC Hendriks, R Heusdens, J Jensen, MMSE based noise PSD tracking with low complexity, in Proc. of IEEE ICASSP (Dallas, Texas, 2010) p. 4266\u20134269","DOI":"10.1109\/ICASSP.2010.5495680"},{"key":"238_CR25","doi-asserted-by":"crossref","unstructured":"Kumar K, Raj B, Singh R, Stern RM, An iterative least-squares technique for dereverberation, in Proc. of ICASSP (Prague, Czech Republic, 2011)","DOI":"10.1109\/ICASSP.2011.5947601"},{"key":"238_CR26","doi-asserted-by":"crossref","unstructured":"Kumar K, Stern RM, Environment-invariant compensation for reverberation using linear post-filtering for minimum distortion, in Proc. of ICASSP (Las Vegas, Nevada, 2008)","DOI":"10.1109\/ICASSP.2008.4518561"},{"issue":"4","key":"238_CR27","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2011","unstructured":"N Dehak, P Kenny, R Dehak, P Dumouchel, P Ouellet, Front-end factor analysis for speaker verification. IEEE. Trans. Audio. Speech. Lang. Process. 19(4), 788\u2013798 (2011)","journal-title":"IEEE. Trans. Audio. Speech. Lang. Process."},{"key":"238_CR28","unstructured":"Kenny P, A small footprint i-vector extractor, in Proc. of Odyssey Speaker and Language Recognition Workshop (Singapore, 2012)"},{"key":"238_CR29","volume-title":"I-Vector\/PLDA Variants for Text-Dependent Speaker Recognition","author":"T Stafylakis","year":"2013","unstructured":"T Stafylakis, P Kenny, P Ouellet, J Perez, M Kockmann, P Dumouchel, I-Vector\/PLDA Variants for Text-Dependent Speaker Recognition (CRIM, Montreal, 2013)"},{"key":"238_CR30","volume-title":"TRAP-Based Probabilistic Features for Automatic Speech Recognition","author":"F Grezl","year":"2007","unstructured":"F Grezl, TRAP-Based Probabilistic Features for Automatic Speech Recognition (Dept. of Computer Graphics & Multimedia, Brno Univ of Technology, Brno, Czech Republic, Doctoral Thesis, 2007)"},{"key":"238_CR31","doi-asserted-by":"crossref","unstructured":"G Saon, H Soltau, D Nahamoo, M Picheny, Speaker adaptation of neural network acoustic models using i-vectors, in Proc. of ASRU (Olomouc, Czech Republic, 2013)","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"238_CR32","doi-asserted-by":"crossref","unstructured":"T Robinson, J Fransen, D Pye, J Foote, S Renals, WSJCAMO: a British English speech corpus for large vocabulary continuous speech recognition, in Proc. of ICASSP (Detroit, Michigan, 1995) p. 81\u201384","DOI":"10.1109\/ICASSP.1995.479278"},{"key":"238_CR33","doi-asserted-by":"crossref","unstructured":"M Lincoln, I McCowan, J Vepa, HK Maganti, The multi-channel Wall Street Journal audio visual corpus (MC-WSJ-AV): specification and initial experiments, in Proc. of ASRU (Cancun, Mexico, 2005) p. 357\u2013362","DOI":"10.1109\/ASRU.2005.1566470"},{"key":"238_CR34","unstructured":"FJ Weninger, S Watanabe, J Le Roux, J Hershey, Y Tachioka, JT Geiger, BW Schuller, G Rigoll, The MERL\/MELCO\/TUM system for the REVERB challenge using deep recurrent neural network feature enhancement, in Proc. of REVERB Challenge Workshop (Florence, Italy, 2014)"},{"key":"238_CR35","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, The REVERB challenge: a common evaluation framework for dereverberation and recognition of reverberant speech, in Proceedings of the WASPAA (New Paltz, NY, 2013)","DOI":"10.1109\/WASPAA.2013.6701894"},{"key":"238_CR36","doi-asserted-by":"crossref","unstructured":"K Vesel\u2019y, A Ghosal, L Burget, D Povey, Sequence discriminative training of deep neural networks, in Proc. of Interspeech (Lyon, France, 2013) p. 2345\u20132349","DOI":"10.21437\/Interspeech.2013-548"},{"key":"238_CR37","volume-title":"Pattern Classification and Scene Analysis","author":"RO Duda","year":"1973","unstructured":"RO Duda, PB Hart, Pattern Classification and Scene Analysis (Wiley, New York, 1973)"},{"issue":"3","key":"238_CR38","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1109\/89.759034","volume":"7","author":"MJF Gales","year":"1999","unstructured":"MJF Gales, Semi-tied covariance matrices for hidden Markov models. IEEE. Trans. Speech. Audio. Process. 7(3), 272\u2013281 (1999)","journal-title":"IEEE. Trans. Speech. Audio. Process."},{"key":"238_CR39","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1006\/csla.1998.0043","volume":"12","author":"MJF Gales","year":"1998","unstructured":"MJF Gales, Maximum likelihood linear transformations for HMM-based speech recognition. Proc. Comput. Speech. Lang. 12, 75\u201398 (1998)","journal-title":"Proc. Comput. Speech. Lang."},{"key":"238_CR40","doi-asserted-by":"crossref","unstructured":"TN Sainath, B Kingsbury, A-R Mohamed, GE Dahl, G Saon, H Soltau, B Beran, AY Aravkin, B Ramabhadran, Improvements to deep convolutional neural networks for LVCSR, in Proceed. of Automatic Speech Recognition and Understanding Workshop (Olomouc, Czech Republic, 2013) p. 315\u2013320,","DOI":"10.1109\/ASRU.2013.6707749"},{"key":"238_CR41","doi-asserted-by":"crossref","unstructured":"D Garcia-Romero, CY Espy-Wilson, Analysis of i-vector length normalization in speaker recognition systems, in Proc. of Interspeech (Florence, Italy, 2011)","DOI":"10.21437\/Interspeech.2011-53"},{"key":"238_CR42","doi-asserted-by":"crossref","unstructured":"V Gupta, G Boulianne, P Kenny, P Ouellet, P Dumouchel, Speaker diarization of French broadcast news, in Proc. of ICASSP (Las Vegas, 2008) p. 4365\u20134368","DOI":"10.1109\/ICASSP.2008.4518622"},{"key":"238_CR43","doi-asserted-by":"crossref","unstructured":"D Paul, B Baker, M Janet, The design for the Wall Street Journal-based CSR corpus, in Proc. of HLT (Harriman, NY, 1992) p. 357\u2013362","DOI":"10.3115\/1075527.1075614"}],"container-title":["EURASIP Journal on Advances in Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s13634-015-0238-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13634-015-0238-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13634-015-0238-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13634-015-0238-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,14]],"date-time":"2022-05-14T00:06:49Z","timestamp":1652486809000},"score":1,"resource":{"primary":{"URL":"https:\/\/asp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13634-015-0238-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,6,19]]},"references-count":43,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2015,12]]}},"alternative-id":["238"],"URL":"https:\/\/doi.org\/10.1186\/s13634-015-0238-6","relation":{},"ISSN":["1687-6180"],"issn-type":[{"value":"1687-6180","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,6,19]]},"assertion":[{"value":"25 February 2015","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 June 2015","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 June 2015","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"50"}}