{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T10:57:25Z","timestamp":1730199445019,"version":"3.28.0"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"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":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389783","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["MASR: Multi-Label Aware Speech Representation"],"prefix":"10.1109","author":[{"given":"Anjali","family":"Raj","sequence":"first","affiliation":[{"name":"Google Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shikhar","family":"Bharadwaj","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sriram","family":"Ganapathy","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Ma","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shikhar","family":"Vashishth","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1873"},{"key":"ref3","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"in Proceedings of 2019 NAACL-HLT","author":"Devlin"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref5","article-title":"Representation learning with contrastive predictive coding","author":"den Oord","year":"2018","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054438"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3200909"},{"article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"in Proceedings of the 34th NeurIPS Conference","author":"Baevski","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref10","first-page":"3915","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","volume-title":"in Proceedings of the 39th ICML","volume":"17","author":"Chiu"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1873"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-011-9125-1"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.03.004"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1242"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414227"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746038"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-854"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-717"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref22","first-page":"27826","article-title":"Unsupervised speech recognition","volume":"34","author":"Baevski","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746097"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2016.7472652"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-15"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref27","article-title":"Deep speaker: an end-to-end neural speaker embedding system","author":"Li","year":"2017","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2070"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-118"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413528"},{"key":"ref32","article-title":"Unispeech: Unified speech representation learning with labeled and unlabeled data","author":"Wang","year":"2021","journal-title":"in ICML. PMLR"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00194"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2437"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2002"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref38","article-title":"Common voice: A massively-multilingual speech corpus","author":"Ardila","year":"2019","journal-title":"in LREC"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"article-title":"Speech recognition and keyword spotting for low-resource languages: Babel project research at cued","volume-title":"in Workshop on Spoken Language Technologies for Underresourced Languages","author":"Francis Gales","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/slt54892.2023.10023141"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21327"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00474"},{"volume-title":"WALS Online (v2020.3), Zenodo","year":"2013","author":"Dryer","key":"ref44"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2023,12,16]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389783.pdf?arnumber=10389783","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:33:41Z","timestamp":1706027621000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389783\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389783","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}