{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:22:15Z","timestamp":1775229735158,"version":"3.50.1"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3419418","type":"journal-article","created":{"date-parts":[[2024,6,28]],"date-time":"2024-06-28T18:44:28Z","timestamp":1719600268000},"page":"3355-3364","source":"Crossref","is-referenced-by-count":29,"title":["SpeechX: Neural Codec Language Model as a Versatile Speech Transformer"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8837-401X","authenticated-orcid":false,"given":"Xiaofei","family":"Wang","sequence":"first","affiliation":[{"name":"Microsoft Corporation, Redmond, WA, USA"}]},{"given":"Manthan","family":"Thakker","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Redmond, WA, USA"}]},{"given":"Zhuo","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Redmond, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8628-3288","authenticated-orcid":false,"given":"Naoyuki","family":"Kanda","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Redmond, WA, USA"}]},{"given":"Sefik Emre","family":"Eskimez","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Redmond, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3082-6052","authenticated-orcid":false,"given":"Sanyuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3428-9967","authenticated-orcid":false,"given":"Min","family":"Tang","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Redmond, WA, USA"}]},{"given":"Shujie","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1089-9748","authenticated-orcid":false,"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Redmond, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7791-3545","authenticated-orcid":false,"given":"Takuya","family":"Yoshioka","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Redmond, WA, USA"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref2","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref5","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Alayrac","year":"2022"},{"key":"ref6","first-page":"1","article-title":"GIT: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.105"},{"key":"ref9","article-title":"AudioPaLM: A large language model that can speak and listen","author":"Rubenstein","year":"2023"},{"key":"ref10","article-title":"MusicLM: Generating music from text","author":"Agostinelli","year":"2023"},{"key":"ref11","first-page":"2709","article-title":"TTS: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Casanova","year":"2022"},{"key":"ref12","first-page":"1","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jia","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1774"},{"key":"ref15","first-page":"1","article-title":"VoiceBox: Text-guided multilingual universal speech generation at scale","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Le","year":"2024"},{"key":"ref16","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00618"},{"key":"ref18","article-title":"Make-a-Voice: Unified voice synthesis with discrete representation","author":"Huang","year":"2023"},{"key":"ref19","article-title":"Speak foreign languages with your own voice: Cross-lingual neural codec language modeling","author":"Zhang","year":"2023"},{"key":"ref20","first-page":"1399","article-title":"A3T: Alignment-aware acoustic and text pretraining for speech synthesis and editing","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Bai","year":"2022"},{"key":"ref21","article-title":"Mega-TTS: Zero-shot text-to-speech at scale with intrinsic inductive bias","author":"Jiang","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1101"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2922820"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746962"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2023.3240008"},{"key":"ref26","article-title":"Universal speech enhancement with score-based diffusion","author":"Serr","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-409"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053182"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref30","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"key":"ref31","first-page":"1","article-title":"NaturalSpeech 2: Latent diffusion models are natural and zero-shot speech and singing synthesizers","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Shen","year":"2024"},{"key":"ref32","first-page":"1","article-title":"High fidelity neural audio compression","author":"Dfossez","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref34","article-title":"MUSAN: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414878"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2024.3378602"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-220"},{"key":"ref41","article-title":"ELLA-V: Stable neural codec language modeling with alignment-guided sequence reordering","author":"Song","year":"2024"},{"key":"ref42","first-page":"1","article-title":"Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Siuzdak","year":"2024"},{"key":"ref43","article-title":"NaturalSpeech 3: Zero-shot speech synthesis with factorized codec and diffusion models","author":"Ju","year":"2024"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10577150.pdf?arnumber=10577150","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,30]],"date-time":"2024-07-30T05:25:51Z","timestamp":1722317151000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10577150\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3419418","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}