{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T21:40:07Z","timestamp":1750369207024,"version":"3.41.0"},"reference-count":19,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,3]]},"DOI":"10.1109\/icassp.2017.7953167","type":"proceedings-article","created":{"date-parts":[[2017,6,20]],"date-time":"2017-06-20T21:35:36Z","timestamp":1497994536000},"page":"5295-5299","source":"Crossref","is-referenced-by-count":8,"title":["Network architectures for multilingual speech representation learning"],"prefix":"10.1109","author":[{"given":"Tom","family":"Sercu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"George","family":"Saon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia","family":"Cui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaodong","family":"Cui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhuvana","family":"Ramabhadran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brian","family":"Kingsbury","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhinav","family":"Sethy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288864"},{"key":"ref12","first-page":"8614","article-title":"Deep convolutional neural networks for lvcsr","author":"tara","year":"2013","journal-title":"2013 IEEE International Conference on Acoustics Speech and Signal Processing"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"simonyan","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"article-title":"Long short-term memory based recurrent neural network architectures for large vocabulary speech recognition","year":"2014","author":"sak","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1033"},{"article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","year":"2015","author":"ioffe","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638951"},{"key":"ref4","article-title":"The spoken term detection (std) 2006 evaluation plan","author":"fiscus","year":"2006","journal-title":"NIST USA Sep"},{"year":"0","author":"harper","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707719"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"2222","DOI":"10.21437\/Interspeech.2013-523","article-title":"Multilingual hierarchical MRASTA features for ASR","author":"tuske","year":"2013","journal-title":"InterSpeech"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639247"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404803"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495646"},{"key":"ref1","article-title":"On the use of a multilingual neural network front-end","author":"scanzio","year":"2008","journal-title":"InterSpeech"},{"key":"ref9","article-title":"Very deep multilingual convolutional neural networks for lvesr","author":"sercu","year":"2016","journal-title":"ICASSP"}],"event":{"name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2017,3,5]]},"location":"New Orleans, LA","end":{"date-parts":[[2017,3,9]]}},"container-title":["2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7943262\/7951776\/07953167.pdf?arnumber=7953167","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T20:58:11Z","timestamp":1750366691000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7953167\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp.2017.7953167","relation":{},"subject":[],"published":{"date-parts":[[2017,3]]}}}