{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T13:37:30Z","timestamp":1762090650224,"version":"build-2065373602"},"reference-count":25,"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\/icasspw59220.2023.10193184","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:54Z","timestamp":1690997454000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["Measuring the Impact of Domain Factors in Self-Supervised Pre-Training"],"prefix":"10.1109","author":[{"given":"Ramon","family":"Sanabria","sequence":"first","affiliation":[{"name":"The University of Edinburgh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Ning","family":"Hsu","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexei","family":"Baevski","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Auli","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-demo.17"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref15","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2021","journal-title":"ICLRE"},{"journal-title":"Weights used for synthesize speech","year":"2021","key":"ref14"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-236"},{"journal-title":"CSTR VCTK corpus English multi-speaker corpus for cstr voice cloning toolkit","year":"2017","key":"ref17"},{"key":"ref16","article-title":"Hifi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"NeurIPS"},{"journal-title":"Montreal forced aligner","year":"0","key":"ref19"},{"journal-title":"The LJ speech dataset","year":"2017","author":"ito","key":"ref18"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.273"},{"key":"ref23","article-title":"Learning Music Helps You Read: Using transfer to study linguistic structure in language models","author":"papadimitriou","year":"2021","journal-title":"EMNLP"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref22","article-title":"The fisher corpus: A resource for the next generations of speech-to-text","author":"cieri","year":"2004","journal-title":"LREC"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096078"},{"key":"ref8","article-title":"Textless speech-to-speech translation on real data","author":"lee","year":"2021","journal-title":"arXiv preprint arXiv 2112 06814"},{"key":"ref7","article-title":"Speech resynthesis from discrete disentangled self-supervised representations","author":"polyak","year":"2021","journal-title":"InterSpeech"},{"key":"ref9","article-title":"Direct speech-to-speech translation with discrete units","author":"lee","year":"2021","journal-title":"arXiv preprint arXiv 2107 05604"},{"key":"ref4","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref5","article-title":"Unsupervised cross-lingual representation learning for speech recognition","author":"conneau","year":"2020","journal-title":"InterSpeech"}],"event":{"name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10192576\/10192577\/10193184.pdf?arnumber=10193184","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:42:37Z","timestamp":1692639757000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10193184\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icasspw59220.2023.10193184","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}