{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:58:43Z","timestamp":1783439923924,"version":"3.54.6"},"reference-count":40,"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\/icassp48485.2024.10447112","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"13326-13330","source":"Crossref","is-referenced-by-count":28,"title":["VoxtLM: Unified Decoder-Only Models for Consolidating Speech Recognition, Synthesis and Speech, Text Continuation Tasks"],"prefix":"10.1109","author":[{"given":"Soumi","family":"Maiti","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Peng","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shukjae","family":"Choi","sequence":"additional","affiliation":[{"name":"42dot Inc,Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jee-Weon","family":"Jung","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuankai","family":"Chang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"issue":"8","key":"ref2","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref3","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NeurIPS","volume":"33","author":"Brown"},{"key":"ref4","first-page":"1336","article-title":"On generative spoken language modeling from raw audio","volume":"9","author":"Lakhotia","year":"2021","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref6","article-title":"Discretalk: Text-to-speech as a machine translation problem","author":"Hayashi","year":"2020"},{"key":"ref7","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3328283"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref10","article-title":"Fast-speech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. ICLR","author":"Ren"},{"key":"ref11","first-page":"5723","article-title":"SpeechT5: Unified-modal encoder-decoder pre-training for spoken language processing","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Ao"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10937"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref16","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022"},{"key":"ref17","article-title":"Slam: A unified encoder for speech and language modeling via speech-text joint pre-training","author":"Bapna","year":"2021"},{"key":"ref18","article-title":"Polyvoice: Language models for speech to speech translation","author":"Dong","year":"2023"},{"key":"ref19","article-title":"Viola: Unified codec language models for speech recognition, synthesis, and translation","author":"Wang","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref21","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref22","article-title":"Textually pre-trained speech language models","author":"Hassid","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1007"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2051"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"ref28","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NeurIPS","volume":"33","author":"Kong"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref30","article-title":"The zero resource speech benchmark 2021: Metrics and baselines for unsupervised spoken language modeling","volume-title":"Proc. NeuRIPS Workshop on Self-Supervised Learning for Speech and Audio Processing","author":"Nguyen"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746395"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref36","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2019-2441","article-title":"Libritts: A corpus derived from librispeech for text-to-speech","volume-title":"Proc. Interspeech","author":"Zen"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.7488\/ds\/2645"},{"key":"ref38","article-title":"Adam: a method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref39","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022656"}],"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\/10447112.pdf?arnumber=10447112","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:46:44Z","timestamp":1722574004000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447112\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447112","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}