{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T16:44:32Z","timestamp":1764002672574,"version":"3.37.3"},"reference-count":50,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"CUHK Stanley Ho Big Data Decision Analytics Research Centre"},{"name":"Center for Perceptual and Interactive Intelligence"},{"name":"Innovation and Technology Commission's InnoHK Scheme"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076144"],"award-info":[{"award-number":["62076144"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["WDZC20220816140515001"],"award-info":[{"award-number":["WDZC20220816140515001"]}]}],"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.2023.3313428","type":"journal-article","created":{"date-parts":[[2023,9,8]],"date-time":"2023-09-08T17:38:56Z","timestamp":1694194736000},"page":"3993-4003","source":"Crossref","is-referenced-by-count":7,"title":["Hiformer: Sequence Modeling Networks With Hierarchical Attention Mechanisms"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9543-1572","authenticated-orcid":false,"given":"Xixin","family":"Wu","sequence":"first","affiliation":[{"name":"Department of Systems Engineering and Engineering Mangement, The Chinese University of Hong Kong, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7698-6262","authenticated-orcid":false,"given":"Hui","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Systems Engineering and Engineering Mangement, The Chinese University of Hong Kong, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6780-4391","authenticated-orcid":false,"given":"Kun","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Systems Engineering and Engineering Mangement, The Chinese University of Hong Kong, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8533-0524","authenticated-orcid":false,"given":"Zhiyong","family":"Wu","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6725-1160","authenticated-orcid":false,"given":"Xunying","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Systems Engineering and Engineering Mangement, The Chinese University of Hong Kong, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4427-3532","authenticated-orcid":false,"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"Department of Systems Engineering and Engineering Mangement, The Chinese University of Hong Kong, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5431"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054345"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1338"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","first-page":"1877","article-title":"Language models are few-shot learners","author":"brown","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"article-title":"Generating sequences with recurrent neural networks","year":"2013","author":"graves","key":"ref10"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3221040"},{"key":"ref16","first-page":"2377","article-title":"Training very deep networks","author":"srivastava","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","article-title":"Hierarchical multiscale recurrent neural networks","author":"chung","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref18","article-title":"FusionNet: Fusing via fully-aware attention with application to machine comprehension","author":"huang","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"article-title":"AISHELL-2: Transforming mandarin ASR research into industrial scale","year":"2018","author":"du","key":"ref50"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414477"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_3"},{"key":"ref47","article-title":"End-to-end ASR: From supervised to semi-supervised learning with modern architectures","author":"synnaeve","year":"0","journal-title":"Proc ICML Workshop Self-Supervision Audio Speech"},{"key":"ref42","first-page":"2142","article-title":"The JRC-Acquis: A multilingual aligned parallel corpus with 20 languages","author":"steinberger","year":"0","journal-title":"Proc Int Conf Lang Resour Eval"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1176"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3115\/1557769.1557821"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12013"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-647"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/29.21701"},{"key":"ref9","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"0","journal-title":"Proc ICML Representation Learn Workshop"},{"key":"ref4","first-page":"16251","article-title":"Neural analysis and synthesis: Reconstructing speech from self-supervised representations","author":"choi","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9883"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.40"},{"article-title":"Layer normalization","year":"2016","author":"ba","key":"ref35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462497"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref36","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301387"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1457"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1098"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.567"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1120"},{"key":"ref38","first-page":"388","article-title":"Statistical significance tests for machine translation evaluation","author":"koehn","year":"0","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref24","article-title":"Incorporating BERT into neural machine translation","author":"zhu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-srw.7"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1191"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1009"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2876404"},{"key":"ref22","first-page":"813","article-title":"Is space-time attention all you need for video understanding?","author":"bertasius","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1175"},{"key":"ref28","first-page":"7955","article-title":"Layer-wise coordination between encoder and decoder for neural machine translation","author":"he","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.72"},{"key":"ref29","article-title":"Understanding and improving encoder layer fusion in sequence-to-sequence learning","author":"liu","year":"0","journal-title":"Proc Int Conf Learn Representations"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10244068.pdf?arnumber=10244068","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:37:15Z","timestamp":1699904235000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10244068\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3313428","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2023]]}}}