{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:57:38Z","timestamp":1776887858317,"version":"3.51.2"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888940","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["CJST: CTC Compressor based Joint Speech and Text Training for Decoder-Only ASR"],"prefix":"10.1109","author":[{"given":"Wei","family":"Zhou","sequence":"first","affiliation":[{"name":"Meta AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junteng","family":"Jia","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leda","family":"Sari","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jay","family":"Mahadeokar","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ozlem","family":"Kalinli","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref2","article-title":"Llama 2: Open foundation and fine-tuned chat models","year":"2023"},{"key":"ref3","article-title":"Gemini: A family of highly capable multimodal models","year":"2024"},{"key":"ref4","article-title":"The Llama 3 herd of models","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447605"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389705"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-705"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref9","article-title":"AudioPaLM: A large language model that can speak and listen","author":"Rubenstein","year":"2023"},{"key":"ref10","article-title":"An embarrassingly simple approach for LLM with strong ASR capacity","author":"Ma","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.57"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448204"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022774"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747862"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10937"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref20","article-title":"Spirit-lm: Interleaved spoken and written language model","author":"Nguyen","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3379877"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.309"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053600"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9415039"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref27","first-page":"3935","article-title":"Enhancing the TED-LIUM corpus with selected data for language modeling and more TED talks","volume-title":"Proc. LREC","author":"Rousseau"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref31","article-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","volume-title":"Int. Conf. on Learning Representations (ICLR)","author":"Simonyan"},{"key":"ref32","first-page":"2613","article-title":"SpecAugment: A Simple Augmentation Method for Automatic Speech Recognition","volume-title":"Proc. Interspeech","author":"Zoph"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888940.pdf?arnumber=10888940","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:02Z","timestamp":1774416242000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888940\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888940","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}