{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:16:02Z","timestamp":1776888962384,"version":"3.51.2"},"reference-count":25,"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\/icassp48485.2024.10447296","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11056-11060","source":"Crossref","is-referenced-by-count":6,"title":["Loss Masking Is Not Needed In Decoder-Only Transformer For Discrete-Token-Based ASR"],"prefix":"10.1109","author":[{"given":"Qian","family":"Chen","sequence":"first","affiliation":[{"name":"Alibaba Group,Speech Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinglin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siqi","family":"Zheng","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiliang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chong","family":"Deng","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yukun","family":"Ma","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hai","family":"Yu","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaqing","family":"Liu","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","volume":"abs\/2303.08774","year":"2023","journal-title":"CoRR"},{"key":"ref2","article-title":"Palm 2 technical report","volume":"abs\/2305.10403","author":"Anil","year":"2023","journal-title":"CoRR"},{"key":"ref3","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref5","article-title":"Viola: Unified codec language models for speech recognition, synthesis, and translation","volume":"abs\/2305.16107","author":"Wang","year":"2023","journal-title":"CoRR"},{"key":"ref6","article-title":"Audiopalm: A large language model that can speak and listen","volume":"abs\/2306.12925","author":"Rubenstein","year":"2023","journal-title":"CoRR"},{"key":"ref7","article-title":"Lauragpt: Listen, attend, understand, and regenerate audio with GPT","volume":"abs\/2310.04673","author":"Wang","year":"2023","journal-title":"CoRR"},{"key":"ref8","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref9","article-title":"vqwav2vec: Self-supervised learning of discrete speech representations","volume-title":"8th International Conference on Learning Representations, ICLR 2020","author":"Baevski"},{"key":"ref10","article-title":"Effectiveness of self-supervised pre-training for speech recognition","volume":"abs\/1911.03912","author":"Baevski","year":"2019","journal-title":"CoRR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2051"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022656"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref16","article-title":"High fidelity neural audio compression","volume":"abs\/2210.13438","author":"D\u00e9fossez","year":"2022","journal-title":"CoRR"},{"key":"ref17","article-title":"Google USM: scaling automatic speech recognition beyond 100 languages","volume":"abs\/2303.01037","author":"Zhang","year":"2023","journal-title":"CoRR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p18-1007"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/19.492748"},{"key":"ref21","article-title":"Distilling the knowledge in a neural network","volume":"abs\/1503.02531","author":"Hinton","year":"2015","journal-title":"CoRR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref25","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019","journal-title":"OpenAI blog"}],"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\/10447296.pdf?arnumber=10447296","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T18:42:22Z","timestamp":1740681742000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447296\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447296","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}