{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:01:48Z","timestamp":1775199708014,"version":"3.50.1"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"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":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434635","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Whisper Has an Internal Word Aligner"],"prefix":"10.1109","author":[{"given":"Sung-Lin","family":"Yeh","sequence":"first","affiliation":[{"name":"University of Edinburgh,Centre for Speech Technology Research,UK"}]},{"given":"Yen","family":"Meng","sequence":"additional","affiliation":[{"name":"University of Edinburgh,Centre for Speech Technology Research,UK"}]},{"given":"Hao","family":"Tang","sequence":"additional","affiliation":[{"name":"University of Edinburgh,Centre for Speech Technology Research,UK"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053182"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.438"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-619"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1855"},{"key":"ref5","article-title":"Ssdm: Scalable speech dysfluency modeling","volume":"37","author":"Lian","year":"2024","journal-title":"NeurIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3485465"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414966"},{"key":"ref8","article-title":"End-to-end continuous speech recognition using attention-based recurrent nn: First results","volume-title":"NIPS 2014 Workshop on Deep Learning","author":"Chorowski"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref11","article-title":"Speech-transformer: a norecurrence sequence-to-sequence model for speech recognition","author":"Dong","year":"2018","journal-title":"ICASSP"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1308"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2029"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.insights-1.11"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1073"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-021-00212-9"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2508"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446111"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889452"},{"key":"ref20","article-title":"whisper-timestamped","author":"Louradour","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-731"},{"key":"ref22","article-title":"Robust speech recognition via largescale weak supervision","author":"Radford","year":"2023","journal-title":"ICML"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-78"},{"key":"ref25","article-title":"Supervised attention in sequence-tosequence models for speech recognition","author":"Yang","year":"2022","journal-title":"ICASSP"},{"key":"ref26","article-title":"Neural machine translation of rare words with subword units","author":"Sennrich","year":"2015","journal-title":"ACL"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1007"},{"key":"ref28","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"Bengio","year":"2015","journal-title":"NeurIPS"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832301"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-343"},{"key":"ref31","article-title":"Opennmt: Neural machine translation toolkit","author":"Klein","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383521"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2231"},{"key":"ref34","article-title":"GlowTTS: A generative flow for text-to-speech via monotonic alignment search","author":"Kim","year":"2020","journal-title":"NeurIPS"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.124"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.6028\/nist.ir.4930"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2007.4430116"},{"key":"ref39","article-title":"The AMI meeting corpus: A preannouncement","volume-title":"International workshop on machine learning for multimodal interaction","author":"Carletta"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1002"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-429"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60276-5_27"},{"key":"ref43","article-title":"Phoneme segmentation using selfsupervised speech models","author":"Strgar","year":"2022","journal-title":"SLT"},{"key":"ref44","article-title":"Supervised attention in sequence-tosequence models for speech recognition","author":"Yang","year":"2022","journal-title":"ICASSP"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2294"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434635.pdf?arnumber=11434635","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:57:35Z","timestamp":1775192255000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434635\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434635","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}