{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T06:29:20Z","timestamp":1775716160809,"version":"3.50.1"},"reference-count":38,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1109\/asru.2015.7404790","type":"proceedings-article","created":{"date-parts":[[2016,2,12]],"date-time":"2016-02-12T08:55:42Z","timestamp":1455267342000},"page":"167-174","source":"Crossref","is-referenced-by-count":434,"title":["EESEN: End-to-end speech recognition using deep RNN models and WFST-based decoding"],"prefix":"10.1109","author":[{"given":"Yajie","family":"Miao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammad","family":"Gowayyed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florian","family":"Metze","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2457612"},{"key":"ref33","article-title":"Improving language-universal feature extraction with deep maxout and convolutional neural networks","author":"miao","year":"2014","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref32","article-title":"Distributed learning of multilingual DNN feature extractors using GPUs","author":"miao","year":"2014","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2001.1034625"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref37","article-title":"Towards speaker adaptive training of deep neural network acoustic models","author":"miao","year":"2014","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424251"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639212"},{"key":"ref34","article-title":"To-wards end-to-end speech recognition for chinese mandarin using long short-term memory recurrent neural networks","author":"li","year":"2015","journal-title":"Annual Conference of the International Speech Communication Association (Inter-speech)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1038"},{"key":"ref11","article-title":"End-to-end attention-based large vocabulary speech recognition","author":"bahdanau","year":"2015","journal-title":"arXiv preprint arXiv 1508 04395"},{"key":"ref12","article-title":"Listen, attend and spell","author":"chan","year":"2015","journal-title":"arXiv preprint arXiv 1508 01211"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178778"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707742"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref18","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"2014","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref28","first-page":"1","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Automatic Speech Recognition and Understanding (ASRU) 2011 IEEE Workshop on"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854675"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2001.0184"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163899"},{"key":"ref6","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proceedings of the 31st International Conference on Machine Learning (ICML-14)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-76336-9_3"},{"key":"ref5","article-title":"Asynchronous, online, GMM-free training of a context dependent acoustic model for speech recognition","author":"bacchiani","year":"2014","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref8","article-title":"First-pass large vocabulary continuous speech recognition using bi-directional recurrent DNNs","author":"hannun","year":"2014","journal-title":"arXiv preprint arXiv 1408 2873"},{"key":"ref7","article-title":"Deepspeech: Scaling up end-to-end speech recognition","author":"hannun","year":"2014","journal-title":"arXiv preprint arXiv 1412 5567"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref9","article-title":"End-to-end continuous speech recognition using attention-based recurrent NN: First results","author":"chorowski","year":"2014","journal-title":"arXiv preprint arXiv 1412 1602"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref20","article-title":"On speaker adaptation of long short-term memory recurrent neural networks","author":"miao","year":"2015","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association (INTERSPEECH)"},{"key":"ref22","first-page":"115","article-title":"Learning precise timing with LSTM recurrent networks","volume":"3","author":"gers","year":"2003","journal-title":"The Journal of Machine Learning Research"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/72.80233"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/29.21701"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref25","article-title":"Deep convolutional neural networks for large-scale speech tasks","author":"sainath","year":"2014","journal-title":"Neural Networks"}],"event":{"name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","location":"Scottsdale, AZ, USA","start":{"date-parts":[[2015,12,13]]},"end":{"date-parts":[[2015,12,17]]}},"container-title":["2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7397480\/7404758\/07404790.pdf?arnumber=7404790","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,22]],"date-time":"2017-03-22T19:08:52Z","timestamp":1490209732000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7404790\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,12]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/asru.2015.7404790","relation":{},"subject":[],"published":{"date-parts":[[2015,12]]}}}