{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:23:09Z","timestamp":1772907789809,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095442","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":24,"title":["LMCodec: A Low Bitrate Speech Codec with Causal Transformer Models"],"prefix":"10.1109","author":[{"given":"Teerapat","family":"Jenrungrot","sequence":"first","affiliation":[{"name":"University of Washington,Seattle"}]},{"given":"Michael","family":"Chinen","sequence":"additional","affiliation":[{"name":"Google"}]},{"given":"W. Bastiaan","family":"Kleijn","sequence":"additional","affiliation":[{"name":"Google"}]},{"given":"Jan","family":"Skoglund","sequence":"additional","affiliation":[{"name":"Google"}]},{"given":"Zal\u00e1n","family":"Borsos","sequence":"additional","affiliation":[{"name":"Google"}]},{"given":"Neil","family":"Zeghidour","sequence":"additional","affiliation":[{"name":"Google"}]},{"given":"Marco","family":"Tagliasacchi","sequence":"additional","affiliation":[{"name":"Google"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10988"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2018.8547084"},{"key":"ref12","author":"borsos","year":"2022","journal-title":"AudioLM a Language Modeling Approach toAudio Generation"},{"key":"ref23","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","author":"yamagishi","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746395"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414901"},{"key":"ref11","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref22","article-title":"ITU-R Recommendation BS 1534-3. Method for the subjective assessment of intermediate quality levels of coding systems","year":"2015","journal-title":"International Telecommunications Union"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref21","first-page":"5206","article-title":"Librispeech: An ASR corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179063"},{"key":"ref1","first-page":"6716","article-title":"Definition of the Opus audio codec","author":"valin","year":"2012","journal-title":"IETF RFC"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1108\/RR-08-2013-0197"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123150"},{"key":"ref18","first-page":"4596","article-title":"Adafactor: Adaptive learning rates with sublinear memory cost","author":"shazeer","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1816"},{"key":"ref7","author":"polyak","year":"2021","journal-title":"Speech resynthesis from discrete disentangled self-supervised representations"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632723"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461487"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.1990.117117"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683277"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095442.pdf?arnumber=10095442","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T14:11:09Z","timestamp":1700489469000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095442\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095442","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}