{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T08:23:57Z","timestamp":1777537437796,"version":"3.51.4"},"reference-count":19,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1109\/icassp.2016.7472152","type":"proceedings-article","created":{"date-parts":[[2016,6,24]],"date-time":"2016-06-24T01:58:30Z","timestamp":1466733510000},"page":"2623-2627","source":"Crossref","is-referenced-by-count":38,"title":["An empirical exploration of CTC acoustic models"],"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":"Xingyu","family":"Na","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tom","family":"Ko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florian","family":"Metze","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Waibel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/11939993_73"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref12","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":"ref13","article-title":"On speaker adaptation of long short-term memory recurrent neural networks","author":"miao","year":"2015","journal-title":"Annual Conference of the International Speech Communication Association (Inter-speech)"},{"key":"ref14","article-title":"Convolutional, long short-term memory, fully connected deep neural networks","author":"tara","year":"2015","journal-title":"Acoustics Speech and Signal Processing (ICASSP) 2015 IEEE International Conference on"},{"key":"ref15","article-title":"Towards 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":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854049"},{"key":"ref17","article-title":"Towards speaker adaptive training of deep neural network acoustic models","author":"miao","year":"2014","journal-title":"Annual Conference of the International Speech Communication Association (Inter-speech)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2457612"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/29.21701"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref3","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":"ref6","article-title":"Deepspeech: Scaling up end-to-end speech recognition","author":"hannun","year":"2014","journal-title":"arXiv preprint arXiv 1412 5567"},{"key":"ref5","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":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref7","article-title":"Fast and accurate recurrent neural network acoustic models for speech recognition","author":"ha?im","year":"2015","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association (INTERSPEECH)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707742"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1109\/TASL.2011.2134090","article-title":"Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition","volume":"20","author":"george","year":"2012","journal-title":"Audio Speech and Language Processing IEEE Transactions on"},{"key":"ref9","first-page":"2342","article-title":"An empirical exploration of recurrent network architectures","author":"jozefowicz","year":"2015","journal-title":"Proceedings of the 32nd International Conference on Machine Learning (ICML-15)"}],"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\/07472152.pdf?arnumber=7472152","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,24]],"date-time":"2017-06-24T17:00:19Z","timestamp":1498323619000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7472152\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp.2016.7472152","relation":{},"subject":[],"published":{"date-parts":[[2016,3]]}}}