{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:07:58Z","timestamp":1776884878267,"version":"3.51.2"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747101","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"8532-8536","source":"Crossref","is-referenced-by-count":26,"title":["Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge Selection"],"prefix":"10.1109","author":[{"given":"Minglun","family":"Han","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linhao","family":"Dong","sequence":"additional","affiliation":[{"name":"Bytedance AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenlin","family":"Liang","sequence":"additional","affiliation":[{"name":"Bytedance AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Cai","sequence":"additional","affiliation":[{"name":"Bytedance AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiyu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zejun","family":"Ma","sequence":"additional","affiliation":[{"name":"Bytedance AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Xu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2416"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1209"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639034"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682738"},{"key":"ref15","first-page":"3490","article-title":"Joint grapheme and phoneme embeddings for contextual end-to-end ASR","author":"chen","year":"2019","journal-title":"InterSpeech"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682441"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383560"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1566"},{"key":"ref19","first-page":"11","article-title":"Contextual RNN-T for open domain ASR","author":"jain","year":"2020","journal-title":"InterSpeech"},{"key":"ref4","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"NIPS"},{"key":"ref28","first-page":"3586","article-title":"Audio augmentation for speech recognition","author":"ko","year":"2015","journal-title":"InterSpeech"},{"key":"ref3","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053205"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref8","first-page":"468","article-title":"Bringing contextual information to google speech recognition","author":"aleksic","year":"2015","journal-title":"InterSpeech"},{"key":"ref7","first-page":"5884","article-title":"Speech-transformer: A no-recurrence sequence-to-sequence model for speech recognition","author":"dong","year":"2018","journal-title":"ICASSP"},{"key":"ref2","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","volume":"32","author":"graves","year":"2014","journal-title":"ICML"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref9","first-page":"1418","article-title":"Composition-based on-the-fly rescoring for salient n-gram biasing","author":"hall","year":"2015","journal-title":"InterSpeech"},{"key":"ref20","first-page":"6528","article-title":"Cifbased collaborative decoding for end-to-end contextual speech recognition","author":"han","year":"2021","journal-title":"ICASSP"},{"key":"ref22","first-page":"4996","article-title":"Weak-attention suppression for transformer based speech recognition","author":"shi","year":"2020","journal-title":"InterSpeech"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054250"},{"key":"ref24","first-page":"5206","article-title":"Librispeech: An ASR corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"ICASSP"},{"key":"ref23","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref25","article-title":"Thekaldispeech recognition toolkit","author":"povey","year":"2011","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747101.pdf?arnumber=9747101","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:11:29Z","timestamp":1661199089000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747101\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747101","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}