{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T05:39:45Z","timestamp":1775281185989,"version":"3.50.1"},"reference-count":27,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2012,1,1]],"date-time":"2012-01-01T00:00:00Z","timestamp":1325376000000},"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":["IEEE Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2012,1]]},"DOI":"10.1109\/tasl.2011.2116010","type":"journal-article","created":{"date-parts":[[2011,2,18]],"date-time":"2011-02-18T17:45:02Z","timestamp":1298051102000},"page":"7-13","source":"Crossref","is-referenced-by-count":97,"title":["Deep and Wide: Multiple Layers in Automatic Speech Recognition"],"prefix":"10.1109","volume":"20","author":[{"given":"Nelson","family":"Morgan","sequence":"first","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.832988"},{"key":"ref11","article-title":"The aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions","author":"hirsch","year":"2000","journal-title":"Proc ISCA ITRW ASR2000 Autom Speech Recognition Challenges for the Next Millennium"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.862024"},{"key":"ref13","author":"bourlard","year":"1993","journal-title":"Connectionist Speech Recognition A Hybrid Approach"},{"key":"ref14","first-page":"1003","article-title":"TRAPS—Classifiers of temporal patterns","author":"hermansky","year":"1998","journal-title":"Proc 5th Int Conf Spoken Lang Process (ICSLP'98)"},{"key":"ref15","author":"chen","year":"2005","journal-title":"Learning discriminant narrow-band temporal patters for automatic recognition of conversational telephone speech"},{"key":"ref16","first-page":"961","article-title":"fPME: Discriminatively trained features for speech recognition","author":"povey","year":"2005","journal-title":"Proc IEEE ICASSP'05"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366992"},{"key":"ref18","first-page":"4165","article-title":"Hierarchical and parallel processing of modulation spectrum for ASR applications","author":"hermansky","year":"2008","journal-title":"Proc IEEE ICASSP'08"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2009-750","article-title":"Hierarchical processing of the modulation spectrum for GALE Mandarin LVCSR system","author":"valente","year":"2009","journal-title":"Proc Interspeech'09"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.759875"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2009.932707"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S0076-5392(08)60492-0"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"3246","DOI":"10.1121\/1.411700","article-title":"Vocal tract normalization in speech recognition: compensation for system systematic speaker variability","volume":"97","author":"cohen","year":"1995","journal-title":"J Acoust Soc Amer"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495666"},{"key":"ref8","first-page":"171","article-title":"Maximum likelihood linear regression for speaker adaptation of continuous density HMMs","volume":"9","author":"leggetter","year":"1995","journal-title":"Speech Commun"},{"key":"ref7","author":"povey","year":"2004","journal-title":"Discriminative training for large vocabulary speech recognition"},{"key":"ref2","author":"dahl","year":"2010","journal-title":"Advances in Neural Information Processing 23"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.879807"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1906946"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2005.1511826"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"2951","DOI":"10.21437\/Interspeech.2009-747","article-title":"Multi-stream to many-stream: Using spectro-temporal features for ASR","author":"zhao","year":"2009","journal-title":"Proc INTERSPEECH"},{"key":"ref21","author":"pinto","year":"2010","journal-title":"Multilayer perceptron based hierarchical acoustic modeling for automatic speech recognition"},{"key":"ref24","author":"chase","year":"1997","journal-title":"Error-Responsive Feedback Mechanisms for Speech Recognizers"},{"key":"ref23","author":"hinton","year":"2010","journal-title":"Personal communication"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2009.932166"},{"key":"ref25","author":"wegmann","year":"2009","journal-title":"Why has (reasonably accurate) automatic speech recognition been so hard to achieve?"}],"container-title":["IEEE Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/10376\/6066252\/05714717.pdf?arnumber=5714717","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,19]],"date-time":"2021-11-19T04:23:25Z","timestamp":1637295805000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5714717\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,1]]},"references-count":27,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tasl.2011.2116010","relation":{},"ISSN":["1558-7916","1558-7924"],"issn-type":[{"value":"1558-7916","type":"print"},{"value":"1558-7924","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,1]]}}}