{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T06:02:36Z","timestamp":1784095356745,"version":"3.55.0"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2014,9,1]],"date-time":"2014-09-01T00:00:00Z","timestamp":1409529600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/I031022\/1"],"award-info":[{"award-number":["EP\/I031022\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","award":["287872"],"award-info":[{"award-number":["287872"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2014,9]]},"DOI":"10.1109\/lsp.2014.2325781","type":"journal-article","created":{"date-parts":[[2014,5,20]],"date-time":"2014-05-20T18:07:30Z","timestamp":1400609250000},"page":"1120-1124","source":"Crossref","is-referenced-by-count":203,"title":["Convolutional Neural Networks for Distant Speech Recognition"],"prefix":"10.1109","volume":"21","author":[{"given":"Pawel","family":"Swietojanski","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arnab","family":"Ghoshal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steve","family":"Renals","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518545"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1999.0128"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"1019","DOI":"10.1038\/14819","article-title":"Hierarchical models of object recognition in cortex","volume":"2","author":"riesenhuber","year":"1999","journal-title":"Nature Neurosci"},{"key":"ref32","article-title":"Exploring convolutional neural network structures and optimisation techniques for speech recognition","author":"abdel-hamid","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref31","article-title":"NumPy Reference","year":"2014"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383157"},{"key":"ref37","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.2003-466","article-title":"From switchboard to fisher: Telephone collection protocols, their uses and yields","author":"cieri","year":"2003","journal-title":"Proc EUROSPEECH"},{"key":"ref36","article-title":"Pylearn2: A machine learning research library","author":"goodfellow","year":"2013","journal-title":"arXiv preprint arXiv 1308 4214"},{"key":"ref35","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc IEEE ASRU"},{"key":"ref34","article-title":"Multiple dimension Levenshtein edit distance calculations for evaluating ASR systems during simultaneous speech","author":"fiscus","year":"2006","journal-title":"Proc LREC"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163900"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/89.759034"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.862024"},{"key":"ref13","article-title":"Using MLP features in SRI?s conversational speech recognition system","author":"zhu","year":"2005","journal-title":"Proc EUROSPEECH"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288833"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707744"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424210"},{"key":"ref18","first-page":"255","author":"lecun","year":"1995","journal-title":"The Handbook of Brain Theory and Neural Networks"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-007-9040-x"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2163395"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707749"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205285"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3210-1"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.4.461"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/5.381844"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/89.260359"},{"key":"ref2","article-title":"Making the most from multiple microphones in meeting recognition","author":"stolcke","year":"2011","journal-title":"Proc IEEE ICASSP"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/9780470714089"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1016\/S0167-6393(01)00058-9","article-title":"Connectionist speech recognition of broadcast news","volume":"37","author":"robinson","year":"2002","journal-title":"Speech Commun"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/29.21701"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319344"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(90)90044-L"},{"key":"ref24","article-title":"Estimating phoneme class conditional probabilities from raw speech signal using convolutional neural networks","author":"palaz","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902460"},{"key":"ref23","article-title":"Convolutional networks for speech detection","author":"sukittanon","year":"2004","journal-title":"Proc ICSLP"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639347"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288864"},{"key":"ref43","first-page":"1096","article-title":"Unsupervised feature learning for audio classification using convolutional deep belief networks","author":"lee","year":"2009","journal-title":"Adv Neural Inf Process Syst 22"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/6818457\/06819043.pdf?arnumber=6819043","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,13]],"date-time":"2023-07-13T08:01:22Z","timestamp":1689235282000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6819043\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,9]]},"references-count":43,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/lsp.2014.2325781","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,9]]}}}