{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:37:07Z","timestamp":1780587427938,"version":"3.54.1"},"reference-count":24,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448454","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"12737-12741","source":"Crossref","is-referenced-by-count":22,"title":["Fewer-Token Neural Speech Codec with Time-Invariant Codes"],"prefix":"10.1109","author":[{"given":"Yong","family":"Ren","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Wang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiangyan","family":"Yi","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Le","family":"Xu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chu Yuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junzuo","family":"Zhou","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00618"},{"key":"ref3","article-title":"Soundstorm: Efficient parallel audio generation","author":"Borsos","year":"2023"},{"key":"ref4","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022"},{"key":"ref5","article-title":"High-fidelity audio compression with improved rvqgan","author":"Kumar","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-537"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1562"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415120"},{"key":"ref11","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","volume-title":"NIPS 2014 Workshop on Deep Learning, December 2014","author":"Chung"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683277"},{"key":"ref13","article-title":"Neural discrete representation learning","volume":"30","author":"Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref15","article-title":"Hifi-codec: Groupresidual vector quantization for high fidelity audio codec","author":"Yang","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref18","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","article-title":"Cross-lingual multi-speaker text-to-speech synthesis for voice cloning without using parallel corpus for unseen speakers","author":"Liu","year":"2019"},{"key":"ref20","article-title":"Aishell3: A multi-speaker mandarin tts corpus and the baselines","author":"Shi","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123150"},{"key":"ref22","article-title":"Perceptual evaluation of speech quality (pesq): An objective method for end-to-end speech quality assessment of narrow-band telephone networks and speech codecs","year":"2001","journal-title":"Rec. ITU-T P. 862"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"}],"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\/10448454.pdf?arnumber=10448454","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:54:07Z","timestamp":1722660847000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448454\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448454","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}