{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:10:36Z","timestamp":1775200236207,"version":"3.50.1"},"reference-count":33,"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\/asru65441.2025.11434761","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Fully Formatted End-to-End Speech Recognition with Knowledge Distillation via Multi-Codebook Vector Quantization"],"prefix":"10.1109","author":[{"given":"Jian","family":"You","sequence":"first","affiliation":[{"name":"Cisco Systems,Shanghai,China"}]},{"given":"Xiangfeng","family":"Li","sequence":"additional","affiliation":[{"name":"Cisco Systems,Shanghai,China"}]},{"given":"Erwan","family":"Zerhouni","sequence":"additional","affiliation":[{"name":"Cisco Systems,Shanghai,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682418"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1250"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3074"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687976"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414518"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-83527-9_7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2367"},{"key":"ref9","first-page":"465","article-title":"An end-to-end model from speech to clean transcript for parliamentary meetings","volume-title":"Asia-Pacific Signal and Information Processing Association Annual Summit and Conference","author":"Mimura"},{"key":"ref10","article-title":"End to end ASR system with automatic punctuation insertion","author":"Guan","year":"2020","journal-title":"arXiv preprint arXiv:2012.02012"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746366"},{"key":"ref13","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1860"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389666"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448264"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448204"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1211.3711"},{"key":"ref20","article-title":"Zipformer: A faster and better encoder for automatic speech recognition","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yao"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095268"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-500"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-775"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-163"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746168"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9413905"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639635"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-797"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p18-1007"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-10051-x"}],"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\/11434761.pdf?arnumber=11434761","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:59:27Z","timestamp":1775192367000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434761\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434761","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}