{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T04:56:30Z","timestamp":1764996990107},"reference-count":37,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,5]]},"DOI":"10.1109\/icassp.2013.6638952","type":"proceedings-article","created":{"date-parts":[[2013,10,29]],"date-time":"2013-10-29T23:19:46Z","timestamp":1383088786000},"page":"6669-6673","source":"Crossref","is-referenced-by-count":111,"title":["A deep convolutional neural network using heterogeneous pooling for trading acoustic invariance with phonetic confusion"],"prefix":"10.1109","author":[{"given":"Li","family":"Deng","sequence":"first","affiliation":[]},{"given":"Ossama","family":"Abdel-Hamid","sequence":"additional","affiliation":[]},{"given":"Dong","family":"Yu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"19","DOI":"10.1109\/TPAMI.2012.268"},{"key":"35","article-title":"Towars deeper understanding: Deep convex networks for semantIc utterance classification","author":"tur","year":"2012","journal-title":"ICASSP"},{"doi-asserted-by":"publisher","key":"17","DOI":"10.1109\/MSP.2012.2205597"},{"year":"2012","author":"hinton","journal-title":"Improving Neural Networks by PreventIng Coadaptation of Feature Detectors 1207","key":"18"},{"key":"36","article-title":"Roles of pretraining and finetuning in context-dependent DNN-HMMs for real-world speech recognition","author":"yu","year":"2010","journal-title":"NIPS Workshop"},{"key":"33","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-569","article-title":"Enhancing exemplar-based posteriors for speech recognItIOn tasks","author":"sainath","year":"2012","journal-title":"InterSpeech"},{"key":"15","article-title":"Deep learning for speech recognition and related applications","author":"deng","year":"2009","journal-title":"NIPS Workshop"},{"key":"34","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-169","article-title":"Conversational speec transcription using context-dependent deep neural networks","author":"seide","year":"2011","journal-title":"InterSpeech"},{"doi-asserted-by":"publisher","key":"16","DOI":"10.1109\/ICASSP.2013.6639344"},{"key":"13","article-title":"Use of differential. Cepstra as acousc features in hidden trajectory modelIng for phonetIc recognition","author":"deng","year":"2007","journal-title":"ICASSP"},{"key":"14","doi-asserted-by":"crossref","DOI":"10.1201\/9781482276237","author":"deng","year":"2003","journal-title":"SPEECH PROCESSIN G-A Dynamic and Optimization-Oriented Approach"},{"doi-asserted-by":"publisher","key":"37","DOI":"10.1109\/TASL.2012.2227738"},{"doi-asserted-by":"publisher","key":"11","DOI":"10.1109\/TSA.2005.854107"},{"doi-asserted-by":"publisher","key":"12","DOI":"10.1109\/TASL.2006.878265"},{"key":"21","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-3","article-title":"Scalabe minimum Bayes risk training of deep neural network acoustIc models using distributed Hessian-free optimization","author":"kingsbury","year":"2012","journal-title":"InterSpeech"},{"key":"20","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-10","article-title":"Application of pretrained deep neural networks to large vocabulary speech recognition","author":"jaitly","year":"2012","journal-title":"InterSpeech"},{"key":"22","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"NIPS"},{"key":"23","article-title":"Tiled convolutional neural networks","author":"le","year":"2010","journal-title":"NIPS"},{"doi-asserted-by":"publisher","key":"24","DOI":"10.1109\/5.726791"},{"doi-asserted-by":"publisher","key":"25","DOI":"10.1109\/CVPR.2004.1315150"},{"doi-asserted-by":"publisher","key":"26","DOI":"10.1109\/TASL.2011.2109382"},{"key":"27","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-304","article-title":"Investigation of fullsequence training of deep belief networks for speech recognition","author":"mohamed","year":"2010","journal-title":"InterSpeech"},{"doi-asserted-by":"publisher","key":"28","DOI":"10.1109\/ICASSP.2011.5947494"},{"doi-asserted-by":"publisher","key":"29","DOI":"10.1109\/TASL.2011.2116010"},{"key":"3","article-title":"Large vocabulary continuous speech recognition with context-dependent DBN-HMMs","author":"dahl","year":"2011","journal-title":"ICASSP"},{"key":"2","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-7","article-title":"Pipelined back-propagation for context-dependent deep neural networks","author":"chen","year":"2012","journal-title":"InterSpeech"},{"doi-asserted-by":"publisher","key":"1","DOI":"10.1109\/ICASSP.2012.6288864"},{"doi-asserted-by":"publisher","key":"10","DOI":"10.1121\/1.1315288"},{"key":"30","article-title":"Multi modal deep learning","author":"ngiam","year":"2011","journal-title":"ICML"},{"doi-asserted-by":"publisher","key":"7","DOI":"10.1109\/ICASSP.2012.6288333"},{"doi-asserted-by":"publisher","key":"6","DOI":"10.1109\/ICASSP.2013.6639345"},{"key":"5","article-title":"Large scaled distributed deep networks","author":"dean","year":"2012","journal-title":"IPS"},{"doi-asserted-by":"publisher","key":"32","DOI":"10.1109\/ASRU.2011.6163900"},{"doi-asserted-by":"publisher","key":"4","DOI":"10.1109\/TASL.2011.2134090"},{"doi-asserted-by":"publisher","key":"31","DOI":"10.1121\/1.429413"},{"doi-asserted-by":"publisher","key":"9","DOI":"10.1109\/SLT.2012.6424224"},{"key":"8","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":"InterSpeech"}],"event":{"name":"ICASSP 2013 - 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2013,5,26]]},"location":"Vancouver, BC, Canada","end":{"date-parts":[[2013,5,31]]}},"container-title":["2013 IEEE International Conference on Acoustics, Speech and Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6619549\/6637585\/06638952.pdf?arnumber=6638952","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,10]],"date-time":"2022-03-10T22:50:09Z","timestamp":1646952609000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6638952\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,5]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp.2013.6638952","relation":{},"subject":[],"published":{"date-parts":[[2013,5]]}}}