{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T21:21:07Z","timestamp":1754601667201},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9054387","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"7699-7703","source":"Crossref","is-referenced-by-count":13,"title":["High-Accuracy and Low-Latency Speech Recognition with Two-Head Contextual Layer Trajectory LSTM Model"],"prefix":"10.1109","author":[{"given":"Jinyu","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eric","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeremy H. M.","family":"Wong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amit","family":"Das","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhong","family":"Meng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Gong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472084"},{"key":"ref32","first-page":"69","article-title":"Investigation of lattice-free maximum mutual information-based acoustic models with sequence-level Kullback-Leibler divergence","author":"kanda","year":"2017","journal-title":"Proc ASRU"},{"article-title":"Distilling the knowledge in a neural network","year":"2015","author":"hinton","key":"ref31"},{"key":"ref30","first-page":"1910","article-title":"Learning small-size DNN with output-distribution-based criteria","author":"li","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639635"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003906"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2971"},{"article-title":"Monotonic chunkwise attention","year":"2017","author":"chiu","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683510"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2001.0182"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2006-603","article-title":"Hypothesis spaces for minimum bayes risk training in large vocabulary speech recognition","author":"gibson","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-275"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref16","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"beaufays","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472780"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-677"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-477"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1485"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2929859"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268937"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1938"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-639","article-title":"Optimizing expected word error rate via sampling for speech recognition","author":"shannon","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2017.7510508"},{"article-title":"Semantic mask for transformer based end-to-end speech recognition","year":"2019","author":"wang","key":"ref7"},{"article-title":"Neural speech recognizer: Acoustic-to-word LSTM model for large vocabulary speech recognition","year":"2016","author":"soltau","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1341"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404793"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-84"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472617"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846305"},{"article-title":"Grid long short-term memory","year":"2015","author":"kalchbrenner","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-911"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683783"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09054387.pdf?arnumber=9054387","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T19:28:26Z","timestamp":1696015706000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054387\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054387","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}