{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T02:59:00Z","timestamp":1774580340135,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,4]]},"DOI":"10.1109\/icassp.2015.7178920","type":"proceedings-article","created":{"date-parts":[[2015,8,12]],"date-time":"2015-08-12T22:45:43Z","timestamp":1439419543000},"page":"4989-4993","source":"Crossref","is-referenced-by-count":98,"title":["An analysis of convolutional neural networks for speech recognition"],"prefix":"10.1109","author":[{"given":"Jui-Ting","family":"Huang","sequence":"first","affiliation":[]},{"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yifan","family":"Gong","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1109\/LSP.2014.2325781","article-title":"Convolutional neural networks for distant speech recognition","author":"swietojanski","year":"2014","journal-title":"IEEE Signal Process Letters"},{"key":"ref11","article-title":"Feature learning in deep neural networks-studies on speech recognition tasks","author":"yu","year":"0","journal-title":"ICLR 2013"},{"key":"ref12","article-title":"Neural network acoustic models for the DARPA RATS program","author":"soltau","year":"0","journal-title":"Proc InterSpeech 2013"},{"key":"ref13","article-title":"Measuring invariances in deep networks","author":"goodfellow","year":"2009","journal-title":"Proc NIPS"},{"key":"ref14","article-title":"Accurate and compact large vocabulary speech recognition on mobile devices","author":"lei","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref15","article-title":"Maxout networks","author":"goodfellow","year":"0","journal-title":"Proc of ICML'2013"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638312"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855088"},{"key":"ref18","article-title":"Spectro-temporal analysis of speech using 2-d Gabor filters","author":"ezzat","year":"2007","journal-title":"Proc INTERSPEECH"},{"key":"ref19","article-title":"Robust CNN-based speech recognition with Gabor filter kernels","author":"chang","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639345"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707749"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639347"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163900"},{"key":"ref1","article-title":"Roles of pretraining and fine-tuning in context-dependent DBN-HMMs for realworld speech recognition","author":"yu","year":"2010","journal-title":"Proc NIPS Workshop on Deep Learning and Unsupervised Feature Learning"},{"key":"ref9","article-title":"Improving language-universal feature extraction with deep maxout and convolutional neural networks","author":"miao","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref20","article-title":"Aurora working group: DSR front end LVCSR evaluation AU\/384\/02","author":"parihar","year":"2002","journal-title":"Tech Rep Inst for Signal and Information Processing"},{"key":"ref22","article-title":"Learning small-size DNN with output-distribution-based criteria","author":"li","year":"0","journal-title":"Proc INTERSPEECH 2014"},{"key":"ref21","article-title":"Microphone array processing for distant speech recognition: towards realworld deployment","author":"kumatani","year":"0","journal-title":"APSIPA Annual Summit and Conference"},{"key":"ref24","first-page":"338","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"2014","journal-title":"InterSpeech"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-015-0068-3"}],"event":{"name":"ICASSP 2015 - 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"South Brisbane, Queensland, Australia","start":{"date-parts":[[2015,4,19]]},"end":{"date-parts":[[2015,4,24]]}},"container-title":["2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7158221\/7177909\/07178920.pdf?arnumber=7178920","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,9,7]],"date-time":"2020-09-07T04:22:56Z","timestamp":1599452576000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7178920\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,4]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp.2015.7178920","relation":{},"subject":[],"published":{"date-parts":[[2015,4]]}}}