{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:23:20Z","timestamp":1753601000148},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447049","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10546-10550","source":"Crossref","is-referenced-by-count":1,"title":["Improving Attention-Based End-to-End Speech Recognition by Monotonic Alignment Attention Matrix Reconstruction"],"prefix":"10.1109","author":[{"given":"Ziyang","family":"Zhuang","sequence":"first","affiliation":[{"name":"Ping An Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Zou","sequence":"additional","affiliation":[{"name":"Ping An Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenfeng","family":"Miao","sequence":"additional","affiliation":[{"name":"Ping An Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Fang","sequence":"additional","affiliation":[{"name":"Ping An Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Wei","sequence":"additional","affiliation":[{"name":"Ping An Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zijian","family":"Li","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Hu","sequence":"additional","affiliation":[{"name":"Ping An Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaojun","family":"Wang","sequence":"additional","affiliation":[{"name":"Ping An Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Xiao","sequence":"additional","affiliation":[{"name":"Ping An Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","volume-title":"ICML","author":"Amodei","key":"ref2"},{"article-title":"Attention-based models for speech recognition","volume-title":"NIPS","author":"Chorowski","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"article-title":"Attention is all you need","volume-title":"NIPS","author":"Vaswani","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414560"},{"article-title":"Unified streaming and non-streaming two-pass end-to-end model for speech recognition","year":"2020","author":"Zhang","key":"ref11"},{"article-title":"Online and linear-time attention by enforcing monotonic alignments","volume-title":"ICML","author":"Raffel","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383606"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003822"},{"article-title":"Monotonic chunkwise attention","volume-title":"ICLR","author":"Chiu","key":"ref15"},{"article-title":"Monotonic multihead attention","volume-title":"ICLR","author":"Ma","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1198"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"article-title":"EfficientTTS: An efficient and high-quality text-to-speech architecture","volume-title":"ICML","author":"Miao","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11259"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1983"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447049.pdf?arnumber=10447049","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:29:04Z","timestamp":1722576544000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447049\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447049","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}