{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T22:23:36Z","timestamp":1757543016631},"reference-count":32,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1109\/icassp.2016.7472641","type":"proceedings-article","created":{"date-parts":[[2016,6,24]],"date-time":"2016-06-24T01:58:30Z","timestamp":1466733510000},"source":"Crossref","is-referenced-by-count":68,"title":["On training the recurrent neural network encoder-decoder for large vocabulary end-to-end speech recognition"],"prefix":"10.1109","author":[{"given":"Liang","family":"Lu","sequence":"first","affiliation":[]},{"given":"Xingxing","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Steve","family":"Renais","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref32","first-page":"187","article-title":"KenLM: Faster and smaller language model queries","author":"heafield","year":"2011","journal-title":"Proceedings of the Sixth Workshop on Statistical Machine Translation"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639345"},{"key":"ref30","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc ASRU"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639211"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078569"},{"key":"ref13","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proc ICML"},{"key":"ref14","article-title":"Fast and accurate recurrent neural network acoustic models for speech recognition","author":"sak","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref16","article-title":"Deep Speech: Scaling up end-to-end speech recognition","author":"hannun","year":"2014","journal-title":"arXiv preprint arXiv 1412 5567"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1038"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref19","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc ICLR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639349"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref27","article-title":"Adadelta: an adaptive learning rate method","author":"zeiler","year":"2012","journal-title":"arXiv preprint arXiv 1212 5701"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"ref5","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref8","article-title":"Sequence-discriminative training of deep neural networks","author":"vesel\u00fd","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref7","article-title":"Scalable minimum Bayes risk training of deep neural network acoustic models using distributed Hessian-free optimization","author":"kingsbury","year":"2012","journal-title":"INTER-SPEECH"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/89.260359"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638951"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3210-1"},{"key":"ref20","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc ICML"},{"key":"ref22","article-title":"A study of the recurrent nerual network encoder-decoder for large vocabulary speech recognition","author":"lu","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref21","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":"ref24","article-title":"Listen, attend and spell","author":"chan","year":"2015","journal-title":"arXiv preprint arXiv 1508 01211"},{"key":"ref23","article-title":"End-to-end attention-based large vocabulary speech recognition","author":"bahdanau","year":"2015","journal-title":"arXiv preprint arXiv 1508 04395"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref25","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Shanghai","start":{"date-parts":[[2016,3,20]]},"end":{"date-parts":[[2016,3,25]]}},"container-title":["2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7465907\/7471614\/07472641.pdf?arnumber=7472641","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2016,10,13]],"date-time":"2016-10-13T16:12:05Z","timestamp":1476375125000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7472641\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp.2016.7472641","relation":{},"subject":[],"published":{"date-parts":[[2016,3]]}}}