{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:56:39Z","timestamp":1776884199771,"version":"3.51.2"},"reference-count":30,"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\/icassp48485.2024.10446203","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10186-10190","source":"Crossref","is-referenced-by-count":14,"title":["Minimally-Supervised Speech Synthesis with Conditional Diffusion Model and Language Model: A Comparative Study of Semantic Coding"],"prefix":"10.1109","author":[{"given":"Chunyu","family":"Qiang","sequence":"first","affiliation":[{"name":"Tianjin University,School of New Media and Communication,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Li","sequence":"additional","affiliation":[{"name":"Kuaishou Technology Co., Ltd,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Ni","sequence":"additional","affiliation":[{"name":"Kuaishou Technology Co., Ltd,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"He","family":"Qu","sequence":"additional","affiliation":[{"name":"Kuaishou Technology Co., Ltd,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruibo","family":"Fu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Wang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longbiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin University,School of New Media and Communication,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwu","family":"Dang","sequence":"additional","affiliation":[{"name":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref2","first-page":"195","article-title":"Deep voice: Real-time neural text-to-speech","volume-title":"International Conference on Machine Learning","author":"Ar\u0131k"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref4","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume":"32","author":"Ren","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","first-page":"8067","article-title":"Glow-tts: A generative flow for text-to-speech via monotonic alignment search","volume":"33","author":"Kim","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414718"},{"key":"ref7","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref8","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3288409"},{"key":"ref10","author":"Wang","year":"2023","journal-title":"Neural codec language models are zero-shot text to speech synthesizers"},{"key":"ref11","author":"Zhang","year":"2023","journal-title":"Speak foreign languages with your own voice: Cross-lingual neural codec language modeling"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00618"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10045"},{"key":"ref14","author":"Shen","year":"2023","journal-title":"Naturalspeech 2: Latent diffusion models are natural and zero-shot speech and singing synthesizers"},{"key":"ref15","author":"Le","year":"2023","journal-title":"Voicebox: Text-guided multilingual universal speech generation at scale"},{"key":"ref16","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref18","author":"D\u00e9fossez","year":"2022","journal-title":"High fidelity neural audio compression"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref20","author":"Gong","year":"2023","journal-title":"Zmm-tts: Zero-shot multilingual and multispeaker speech synthesis conditioned on self-supervised discrete speech representations"},{"key":"ref21","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref24","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095840"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref27","author":"van den Oord","year":"2016","journal-title":"Wavenet: A generative model for raw audio"},{"key":"ref28","author":"Kingma","year":"2014","journal-title":"Adam: A method for stochastic optimization"},{"key":"ref29","author":"Shi","year":"2020","journal-title":"Aishell-3: A multi-speaker mandarin tts corpus and the baselines"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9980115"}],"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\/10446203.pdf?arnumber=10446203","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:31:18Z","timestamp":1722573078000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446203\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446203","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}