{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:59:56Z","timestamp":1777611596113,"version":"3.51.4"},"reference-count":96,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2013,5,1]],"date-time":"2013-05-01T00:00:00Z","timestamp":1367366400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. IEEE"],"published-print":{"date-parts":[[2013,5]]},"DOI":"10.1109\/jproc.2012.2236871","type":"journal-article","created":{"date-parts":[[2013,2,1]],"date-time":"2013-02-01T19:47:32Z","timestamp":1359748052000},"page":"1076-1088","source":"Crossref","is-referenced-by-count":24,"title":["Multistream Recognition of Speech: Dealing With Unknown Unknowns"],"prefix":"10.1109","volume":"101","author":[{"given":"Hynek","family":"Hermansky","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","first-page":"37","article-title":"Using missing feature theory to actively select features for robust speech recognition with interruptions, filtering and noise","author":"lippmann","year":"1997","journal-title":"Proc EUROSPEECH"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1121\/1.1906605"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2023162"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518547"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.12.004"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.4159\/harvard.9780674419193"},{"key":"ref39","first-page":"462","article-title":"Towards ASR on partially corrupted speech","author":"hermansky","year":"1996","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref74","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1063\/1.2821301","article-title":"Towards a cross-level theory of neural learning","volume":"954","author":"bell","year":"2008","journal-title":"Proc 27th Int Workshop Bayesian Inference Maximum Entropy Methods Sci Eng"},{"key":"ref38","first-page":"1579","article-title":"Towards subband-based speech recognition","author":"bourlard","year":"1996","journal-title":"Proc EUSIPCO"},{"key":"ref75","doi-asserted-by":"crossref","first-page":"2329","DOI":"10.21437\/Interspeech.2011-618","article-title":"Adaptive stream fusion in multistream recognition of speech","author":"mesgarani","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907526"},{"key":"ref79","doi-asserted-by":"crossref","first-page":"318","DOI":"10.21437\/Interspeech.2010-120","article-title":"A multistream multiresolution framework for phoneme recognition","author":"mesgarani","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2007.2159"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1037\/0278-7393.20.4.786"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1037\/0278-7393.25.2.394"},{"key":"ref30","first-page":"83","author":"kutas","year":"1994","journal-title":"Handbook of Psycholinguistics"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1037\/11135-000"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1126\/science.1105783"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1111\/j.0963-7214.2005.00327.x"},{"key":"ref34","first-page":"141","article-title":"Performance monitoring in confusing word: Error brain activity, judgments of response accuracy, and types of errors","volume":"26","author":"sheffers","year":"2000","journal-title":"J Exp Psychol"},{"key":"ref60","author":"jain","year":"2003","journal-title":"Temporal patterns of frequency-localized features in ASR"},{"key":"ref62","first-page":"25","article-title":"Improving word accuracy with Gabor feature extraction","author":"kleinschmidt","year":"2002","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref61","first-page":"906","article-title":"Optimization and evaluation of Gabor feature sets for ASR","author":"meyer","year":"2009","journal-title":"Proc INTERSPEECH"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"1187","DOI":"10.1126\/science.150.3700.1187","article-title":"Evoked potential correlates of stimulus uncertainty","author":"sutton","year":"1965","journal-title":"Science"},{"key":"ref63","doi-asserted-by":"crossref","first-page":"898","DOI":"10.21437\/Interspeech.2008-209","article-title":"Multi-stream spectro-temporal features for robust speech recognition","author":"zhao","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"392","DOI":"10.1126\/science.167.3917.392","article-title":"Perceptual restoration of missing speech sounds","volume":"167","author":"warren","year":"1970","journal-title":"Science"},{"key":"ref64","doi-asserted-by":"crossref","first-page":"2458","DOI":"10.21437\/Interspeech.2010-661","article-title":"A phoneme recognition framework based on auditory spectro-temporal receptive fields","author":"thomas","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref65","first-page":"1757","article-title":"Detection of out-of-vocabulary words in posterior based ASR","author":"ketabdar","year":"2007","journal-title":"Proc INTERSPEECH"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1111\/1469-8986.3810001"},{"key":"ref66","first-page":"4081","article-title":"Combination of strongly and weakly constrained recognizers for reliable detection of out-of-vocabulary words (OOVs)","author":"burget","year":"2008","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref67","doi-asserted-by":"crossref","first-page":"80","DOI":"10.21437\/Interspeech.2009-18","article-title":"Posterior-based out-of-vocabulary word detection in telephone speech","author":"kombrink","year":"2009","journal-title":"Proc INTERSPEECH"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15760-8_42"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1121\/1.1911801"},{"key":"ref69","doi-asserted-by":"crossref","first-page":"897","DOI":"10.21437\/Interspeech.2010-300","article-title":"Similarity scoring for recognizing repeated out-of-vocabulary words","author":"hannemann","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref1","author":"church","year":"2012","journal-title":"Personal Communications JHU Summer Miniworkshop on Zero Resources ASR"},{"key":"ref20","author":"rankovic","year":"2000","journal-title":"Study of Speech and Hearing at Bell Telephone Laboratories The Fletcher Years Correspondence Files Internal Reports and Several of the Many Lab Notebooks of R Galt (19171933)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pbio.0060016"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1121\/1.3699231"},{"key":"ref24","author":"pickles","year":"1988","journal-title":"An Introduction to the Physiology of Hearing"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1002\/cne.900950109"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1121\/1.2816572"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.23.1.501"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2116010"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(00)00044-3"},{"key":"ref95","doi-asserted-by":"crossref","first-page":"928","DOI":"10.21437\/Interspeech.2008-110","article-title":"Using KL-based acoustic models in a large vocabulary recognition task","author":"aradilla","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.862024"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2129510"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2116010"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109382"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref96","first-page":"5028","article-title":"Dirichlet mixture models of neural net posteriors for HMM-based speech recognition","author":"balakrishnan","year":"2011","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref59","doi-asserted-by":"crossref","first-page":"1017","DOI":"10.21437\/Eurospeech.2003-202","article-title":"Local averaging and differentiating of spectral plane for TRAP-based ASR","author":"grezl","year":"2003","journal-title":"Proc EUROSPEECH"},{"key":"ref58","author":"valente","year":"2011","journal-title":"Handbook of Natural Language Processing and Machine Translation DARPA Global Autonomous Language Exploitation"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1202473"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.675346"},{"key":"ref55","first-page":"361","article-title":"Multi-resolution RASTA filtering for TANDEM-based ASR","author":"hermansky","year":"2005","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref54","article-title":"TRAPS, classifiers of temporal patterns","author":"hermansky","year":"1998","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s12046-011-0044-2"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5494907"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JRPROC.1949.232969"},{"key":"ref11","author":"fletcher","year":"1953","journal-title":"Speech and hearing in communication"},{"key":"ref40","first-page":"426","article-title":"A new ASR approach based on independent processing and re-combination of partial frequency bands","author":"bourlard","year":"1996","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-02554-9","author":"allen","year":"2005","journal-title":"Articulation and Intelligibility"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1121\/1.408434"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.tins.2010.11.002"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2005.1511828"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1037\/h0062491"},{"key":"ref82","author":"ogawa","year":"2012","journal-title":"Stream selection and integration in multi-stream ASR using GMM-based performance monitoring"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1121\/1.396976"},{"key":"ref81","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-490","article-title":"Estimating classifier performance in unknown noise","author":"variani","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4959922"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1121\/1.3595744"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1121\/1.399061"},{"key":"ref83","author":"variani","year":"2012","journal-title":"Multi-stream recognition of noisy speech with performance monitoring"},{"key":"ref80","first-page":"4780","article-title":"A performance monitoring approach to fusing enhanced spectrogram channels in robust speech recognition","author":"badiezadegan","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref4","year":"2011","journal-title":"Handbook of Natural Language Processing and Machine Translation DARPA Global Autonomous Language Exploitation"},{"key":"ref89","doi-asserted-by":"crossref","first-page":"437","DOI":"10.21437\/Interspeech.2011-169","article-title":"Conversational speech transcription using context-dependent deep neural networks","author":"seide","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1976.10159"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1541880.1541882"},{"key":"ref5","article-title":"Clausewitz and modern war gaming: Losing can be better than winning","author":"furlong","year":"1984","journal-title":"Air Univ Rev"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1995.0010"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1155\/2007\/42357"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.12.007"},{"key":"ref49","author":"sharma","year":"1999","journal-title":"Multi-stream Approach to Robust Speech Recognition"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/78.978374"},{"key":"ref87","first-page":"93","article-title":"The DARPA speech recognition research database: Specifications and status","author":"fisher","year":"1986","journal-title":"Proc DARPA Workshop Speech Recognit"},{"key":"ref9","year":"2012","journal-title":"Techniques for Noise Robustness in Automatic Speech Recognition"},{"key":"ref88","author":"hermansky","year":"2012","journal-title":"Mean temporal distance Predicting ASR error from temporal properties of speech signal"},{"key":"ref46","author":"allen","year":"1993","journal-title":"Personal communication"},{"key":"ref45","author":"duchnowski","year":"1992","journal-title":"A new structure for automatic speech recognition"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.596173"},{"key":"ref47","author":"bourlard","year":"1993","journal-title":"Connectionist Speech Recognition A Hybrid Approach"},{"key":"ref42","first-page":"1","article-title":"Non-stationary multi-channel (multi-stream) processing towards robust and adaptive ASR","author":"bourlard","year":"1999","journal-title":"Proc ESCA Workshop Robust Methods Speech Recognit Adverse Conditions"},{"key":"ref41","first-page":"1255","article-title":"Multi-stream approach in acoustic modeling","author":"tibrewala","year":"1997","journal-title":"Proc DARPA Large Vocabulary Cont Speech Recognit Hub 5 Workshop"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1080\/14640749108400991"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.1997.659110"}],"container-title":["Proceedings of the IEEE"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5\/6504474\/06428587.pdf?arnumber=6428587","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,29]],"date-time":"2023-06-29T04:19:35Z","timestamp":1688012375000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6428587\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,5]]},"references-count":96,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/jproc.2012.2236871","relation":{},"ISSN":["0018-9219","1558-2256"],"issn-type":[{"value":"0018-9219","type":"print"},{"value":"1558-2256","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,5]]}}}