{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:55:27Z","timestamp":1783439727282,"version":"3.54.6"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2014,10,1]],"date-time":"2014-10-01T00:00:00Z","timestamp":1412121600000},"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\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2014,10]]},"DOI":"10.1109\/taslp.2014.2339736","type":"journal-article","created":{"date-parts":[[2014,7,16]],"date-time":"2014-07-16T18:38:36Z","timestamp":1405535916000},"page":"1533-1545","source":"Crossref","is-referenced-by-count":1835,"title":["Convolutional Neural Networks for Speech Recognition"],"prefix":"10.1109","volume":"22","author":[{"given":"Ossama","family":"Abdel-Hamid","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdel-rahman","family":"Mohamed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gerald","family":"Penn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638952"},{"key":"ref38","article-title":"Exploring convolutional neural network structures and optimization techniques for speech recognition","author":"abdel-hamid","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref33","first-page":"1096","article-title":"Unsupervised feature learning for audio classification using convolutional deep belief networks","author":"lee","year":"2009","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/BF00344251"},{"key":"ref31","author":"lecun","year":"1995","journal-title":"The Handbook of Brain Theory and Neural Networks"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424210"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288864"},{"key":"ref36","article-title":"Feature learning in deep neural networks - studies on speech recognition tasks","author":"yu","year":"2013","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/29.21701"},{"key":"ref34","article-title":"Exploring hierarchical speech representations using a deep convolutional neural network","author":"hau","year":"2011","journal-title":"Proc 11th UK Workshop Comput Intell (UKCI '11)"},{"key":"ref10","article-title":"Deep belief networks for phone recognition","author":"mohamed","year":"2009","journal-title":"Proc NIPS Workshop Deep Learn Speech Recogn Relat Applicat"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639347"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"2846","DOI":"10.21437\/Interspeech.2010-304","article-title":"Investigation of full-sequence training of deep belief networks for speech recognition","author":"mohamed","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288333"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref14","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":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163900"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2012.6423452"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref18","first-page":"531","article-title":"Learning a minimally structured back propagation network to recognize speech","author":"landauer","year":"1987","journal-title":"Proc 9th Annu Conf Cogn Sci Soc"},{"key":"ref19","article-title":"A neural network digit recognizer","author":"burr","year":"1986","journal-title":"Proc IEEE Int Conf Syst Man Cybern"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760128018"},{"key":"ref4","article-title":"Phone recognition with the mean-covariance restricted Boltzmann machine","author":"dahl","year":"2010","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref27","author":"bourlard","year":"1993","journal-title":"Connectionist Speech Recognition A Hybrid Approach"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2244083"},{"key":"ref6","article-title":"Roles of pre-training and fine-tuning in context-dependent DBN-HMMs for real-world speech recognition","author":"yu","year":"2010","journal-title":"Proc NIPS Workshop on Deep Learning and Unsupervised Feature Learning"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288863"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947494"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163899"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947401"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2008.926652"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2116010"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2009.08.002"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109382"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1007\/978-3-540-30568-2_19","volume":"3361","author":"zhu","year":"2005","journal-title":"Machine Learning for Multimodal Interaction"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553453"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/29.46546"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.862024"},{"key":"ref42","author":"sak","year":"2014","journal-title":"?Long short-term memory based recurrent neural network architectures for large vocabulary speech recognition ?"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639015"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947494"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-487","article-title":"Binary coding of speech spectrograms using a deep auto-encoder","author":"deng","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref44","first-page":"92","article-title":"Evaluation of pooling operations in convolutional architectures for object recognition","author":"scherer","year":"2010","journal-title":"Proc Int'l Conf Artificial Neural Networks Part 2"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(94)90027-2"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639344"},{"key":"ref25","author":"zhang","year":"1994","journal-title":"A Pipelined Neural Network Architecture For Speech Recognition In Book VLSI Artificial Neural Networks Engineering"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/6860345\/06857341.pdf?arnumber=6857341","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,11]],"date-time":"2022-04-11T07:22:48Z","timestamp":1649661768000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6857341\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,10]]},"references-count":47,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2014.2339736","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,10]]}}}