{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:29:46Z","timestamp":1775230186173,"version":"3.50.1"},"reference-count":114,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2021.3133217","type":"journal-article","created":{"date-parts":[[2021,12,7]],"date-time":"2021-12-07T20:41:37Z","timestamp":1638909697000},"page":"1371-1385","source":"Crossref","is-referenced-by-count":8,"title":["Alignment Knowledge Distillation for Online Streaming Attention-Based Speech Recognition"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0610-1251","authenticated-orcid":false,"given":"Hirofumi","family":"Inaguma","sequence":"first","affiliation":[{"name":"Graduate School of Informatics, Kyoto University, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2686-2296","authenticated-orcid":false,"given":"Tatsuya","family":"Kawahara","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Kyoto University, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054188"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1705"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053600"},{"key":"ref8","first-page":"577","article-title":"Attention-based models for speech recognition","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst.","author":"Chorowski","year":"2015"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-233"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268937"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003834"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2846"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639690"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003906"},{"key":"ref17","article-title":"A neural transducer","author":"Jaitly","year":"2015"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683510"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682500"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054250"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1972"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-334"},{"key":"ref24","first-page":"431","article-title":"Local monotonic attention mechanism for end-to-end speech and language processing","volume-title":"Proc. Int. Joint Conf. Natural Lang. Process.","author":"Tjandra","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-751"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.31390\/gradschool_dissertations.4601"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952667"},{"key":"ref28","article-title":"Monotonic chunkwise attention","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chiu","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004027"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2018"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2218"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054098"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2987752"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003854"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-350"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-275"},{"key":"ref37","first-page":"604","article-title":"Acoustic modelling with CD-CTC-sMBR LSTM RNNs","volume-title":"Proc. IEEE Autom. Speech Recognit. Understanding Workshop","author":"Sak","year":"2015"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1049"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054663"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383606"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1069"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref44","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref45","first-page":"5067","article-title":"An online sequence-to-sequence model using partial conditioning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Jaitly","year":"2016"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462366"},{"key":"ref47","article-title":"Adaptive computation time for recurrent neural networks","author":"Graves","year":"2016"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383563"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003920"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054476"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1292"},{"key":"ref52","article-title":"Learning monotonic alignments with source-aware GMM attention","author":"Kang","year":"2021"},{"key":"ref53","article-title":"An online sequence-to-sequence model for noisy speech recognition","author":"Chiu","year":"2017"},{"key":"ref54","first-page":"2837","article-title":"Online and linear-time attention by enforcing monotonic alignments","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Raffel","year":"2017"},{"key":"ref55","article-title":"Towards online end-to-end Transformer automatic speech recognition","author":"Tsunoo","year":"2019"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1780"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383613"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2985"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2897"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1114"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383517"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178778"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1059"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413803"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413899"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414607"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1110"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-322"},{"key":"ref69","article-title":"Dual-mode ASR: Unify and improve streaming ASR with full-context modeling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu","year":"2021"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461995"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2517"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1589"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1025"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639629"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683171"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2442"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413905"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1952"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3019917"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053578"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1223"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref83","volume-title":"The Application of Hidden Markov Models in Speech Recognit.","author":"Gales","year":"2008"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1972"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3031480"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413613"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472780"},{"key":"ref88","first-page":"125","article-title":"TED-LIUM: An automatic speech recognition dedicated corpus","volume-title":"Proc. 8th Int. Conf. Lang. Resour. Eval.","author":"Rousseau","year":"2012"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref90","article-title":"Corpus of Spontaneous Japanese: Its design and evaluation","volume-title":"Proc. ISCA IEEE Workshop Spontaneous Speech Process. Recognit.","author":"Maekawa","year":"2003"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_3"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref93","article-title":"The Kaldi speech recognition toolkit","volume-title":"Proc. IEEE Autom. Speech Recognit. Understanding Workshop","author":"Povey","year":"2011"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3018"},{"key":"ref96","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003822"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1778"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004025"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003936"},{"key":"ref102","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-79"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1475"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1887"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054715"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053040"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1007\/s10590-008-9047-0"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.3115\/1620754.1620810"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-301"},{"key":"ref112","first-page":"110","article-title":"Stability and accuracy in incremental speech recognition","volume-title":"Proc. 12th Annu. Meeting Special Interest Group Discourse Dialogue","author":"Selfridge","year":"2011"},{"key":"ref113","article-title":"Low latency ASR for simultaneous speech translation","author":"Nguyen","year":"2020"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1194"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/09640576.pdf?arnumber=9640576","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T01:46:58Z","timestamp":1710380818000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9640576\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":114,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3133217","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}