{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:43:30Z","timestamp":1730231010853,"version":"3.28.0"},"reference-count":33,"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\/icassp49357.2023.10096681","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Leveraging Language Embeddings for Cross-Lingual Self-Supervised Speech Representation Learning"],"prefix":"10.1109","author":[{"given":"Tomohiro","family":"Tanaka","sequence":"first","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryo","family":"Masumura","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mana","family":"Ihori","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroshi","family":"Sato","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taiga","family":"Yamane","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takanori","family":"Ashihara","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kohei","family":"Matsuura","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takafumi","family":"Moriya","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref15","article-title":"Cross-lingual ability of multilingual BERT: an empirical study","author":"k","year":"2020","journal-title":"In Proc of International Conference on Learning Representations (ICLR)"},{"key":"ref14","first-page":"7057","article-title":"Cross-lingual language model pretraining","author":"conneau","year":"2019","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref30","first-page":"244","article-title":"A Japanese national project on spontaneous speech corpus and processing technology","author":"furui","year":"2000","journal-title":"In Proc of ASR2000 - Automatic Speech Recognition Challenges for the new Millenium"},{"key":"ref11","first-page":"1298","article-title":"data2vec: A general framework for self-supervised learning in speech, vision and language","volume":"162","author":"baevski","year":"2022","journal-title":"Proc of International Conference on Machine Learning (ICML-05)"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref32","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref1","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"In Proc of Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies (NAACL-HLT)"},{"key":"ref17","first-page":"10937","article-title":"Unispeech: Unified speech representation learning with labeled and unlabeled data","volume":"139","author":"wang","year":"2021","journal-title":"Proc of International Conference on Machine Learning (ICML-05)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.106"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-143"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687871"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11249"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2831"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2485"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747671"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003870"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2164"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461972"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-216"},{"key":"ref29","article-title":"Categorical reparameterization with gumbel-softmax","author":"jang","year":"2017","journal-title":"In Proc of International Conference on Learning Representations (ICLR)"},{"key":"ref8","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2020","journal-title":"In Proc of International Conference on Learning Representations (ICLR)"},{"key":"ref7","first-page":"3465","article-title":"wav2vec: Un-supervised pre-training for speech recognition","author":"schneider","year":"2019","journal-title":"In Proc of Conference of the International Speech Communication Association (INTERSPEECH)"},{"key":"ref9","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref3","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","author":"lan","year":"2020","journal-title":"In Proc of International Conference on Learning Representations (ICLR)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","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\/10096681.pdf?arnumber=10096681","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T18:59:48Z","timestamp":1700506788000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096681\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096681","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}