{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:38:58Z","timestamp":1776886738591,"version":"3.51.2"},"reference-count":39,"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\/icassp48485.2024.10448074","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11546-11550","source":"Crossref","is-referenced-by-count":8,"title":["Extending Multilingual Speech Synthesis to 100+ Languages without Transcribed Data"],"prefix":"10.1109","author":[{"given":"Takaaki","family":"Saeki","sequence":"first","affiliation":[{"name":"Google,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gary","family":"Wang","sequence":"additional","affiliation":[{"name":"Google,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nobuyuki","family":"Morioka","sequence":"additional","affiliation":[{"name":"Google DeepMind,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Isaac","family":"Elias","sequence":"additional","affiliation":[{"name":"Google,Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyle","family":"Kastner","sequence":"additional","affiliation":[{"name":"Google,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Rosenberg","sequence":"additional","affiliation":[{"name":"Google,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhuvana","family":"Ramabhadran","sequence":"additional","affiliation":[{"name":"Google,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heiga","family":"Zen","sequence":"additional","affiliation":[{"name":"Google DeepMind,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fran\u00e7oise","family":"Beaufays","sequence":"additional","affiliation":[{"name":"Google,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hadar","family":"Shemtov","sequence":"additional","affiliation":[{"name":"Google DeepMind,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"5410","article-title":"Almost unsupervised text to speech and automatic speech recognition","volume-title":"ICML","author":"Ren"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683862"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1403"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00618"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-816"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/575"},{"key":"ref7","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref9","first-page":"3915","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","volume-title":"ICML","author":"Chiu"},{"key":"ref10","article-title":"mSLAM: Massively multilingual joint pre-training for speech and text","author":"Bapna","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10937"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/slt54892.2023.10022791"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-277"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26488"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10797"},{"key":"ref16","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref17","article-title":"MLS: A large-scale multilingual dataset for speech research","author":"Pratap","year":"2019"},{"key":"ref18","first-page":"16","article-title":"Speech recognition and keyword spotting for low-resource languages: Babel project research at CUED","volume-title":"SLTU","author":"Gales"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref20","article-title":"FLEURS: Few-shot learning evaluation of universal representations of speech","author":"Conneau","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2187195"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-172"},{"key":"ref23","article-title":"Multilingual Byte2Speech models for scalable low-resource speech synthesis","author":"He","year":"2021"},{"key":"ref24","article-title":"Virtuoso: Massive multilingual speech-text joint semi-supervised learning for text-to-speech","author":"Saeki","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.472"},{"key":"ref26","article-title":"Scaling speech technology to 1,000+ languages","author":"Pratap","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref28","article-title":"Google USM: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022496"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268950"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414718"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1461"},{"key":"ref33","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1077"},{"key":"ref36","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"NAACL","author":"Devlin"},{"key":"ref37","article-title":"Mass: Masked sequence to sequence pre-training for language generation","author":"Song","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.41"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10094909"}],"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\/10448074.pdf?arnumber=10448074","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:29:42Z","timestamp":1722572982000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448074\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448074","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}