{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:57:29Z","timestamp":1776884249605,"version":"3.51.2"},"reference-count":32,"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\/icassp48485.2024.10447520","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10716-10720","source":"Crossref","is-referenced-by-count":11,"title":["Multilingual Distilwhisper: Efficient Distillation of Multi-Task Speech Models Via Language-Specific Experts"],"prefix":"10.1109","author":[{"given":"Thomas Palmeira","family":"Ferraz","sequence":"first","affiliation":[{"name":"Naver Labs,Europe,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcely","family":"Zanon Boito","sequence":"additional","affiliation":[{"name":"Naver Labs,Europe,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Caroline","family":"Brun","sequence":"additional","affiliation":[{"name":"Naver Labs,Europe,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vassilina","family":"Nikoulina","sequence":"additional","affiliation":[{"name":"Naver Labs,Europe,France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"ICML","author":"Radford"},{"key":"ref2","article-title":"Esb: A benchmark for multi-domain end-to-end speech recognition","author":"Gandhi","year":"2022"},{"key":"ref3","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"Massively multilingual neural machine translation in the wild: Findings and challenges","author":"Arivazhagan","year":"2019"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2020.acl-main.747","article-title":"Unsupervised cross-lingual representation learning at scale","volume-title":"ACL","author":"Conneau"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.repl4nlp-1.4"},{"key":"ref7","article-title":"Distilbert, a distilled version of BERT: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"CoRR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.571"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.255"},{"key":"ref10","article-title":"Scaling speech technology to 1,000+ languages","author":"Pratap","year":"2023"},{"key":"ref11","article-title":"Share or not? learning to schedule language-specific capacity for multilingual translation","volume-title":"ICLR","author":"Zhang"},{"key":"ref12","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"ICLR","author":"Hu"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-143"},{"key":"ref17","article-title":"Google usm: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023"},{"key":"ref18","article-title":"Distilling the knowledge in a neural network","volume-title":"NIPS Deep Learning and Representation Learning Workshop","author":"Hinton"},{"key":"ref19","article-title":"Language-universal adapter learning with knowledge distillation for end-to-end multilingual speech recognition","author":"Shen","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.605"},{"key":"ref21","article-title":"Aligning language models with preferences through f-divergence minimization","author":"Go","year":"2023","journal-title":"ICML"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.103"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.iwslt-1.10"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.iwslt-1.10"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746223"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.541"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1407"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1505"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ACII59096.2023.10388152"},{"key":"ref30","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"LREC","author":"Ardila"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023141"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"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\/10447520.pdf?arnumber=10447520","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:47:33Z","timestamp":1722574053000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447520\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447520","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}