{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T15:13:01Z","timestamp":1725808381500},"reference-count":33,"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\/icassp48485.2024.10448215","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11526-11530","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal Modeling for Spoken Language Identification"],"prefix":"10.1109","author":[{"given":"Shikhar","family":"Bharadwaj","sequence":"first","affiliation":[{"name":"Google"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Ma","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shikhar","family":"Vashishth","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ankur","family":"Bapna","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sriram","family":"Ganapathy","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vera","family":"Axelrod","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siddharth","family":"Dalmia","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Han","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daan","family":"Van Esch","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sandy","family":"Ritchie","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Partha","family":"Talukdar","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jason","family":"Riesa","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2237151"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2164"},{"key":"ref3","first-page":"1798","article-title":"Performance analysis of the 2017 NIST Language Recognition Evaluation","volume-title":"Interspeech","author":"Omid"},{"key":"ref4","first-page":"82","article-title":"The 2017 NIST Language Recognition Evaluation","author":"Omid","year":"2018","journal-title":"Odyssey"},{"article-title":"Vast: A corpus of video annotation for speech technologies","volume-title":"Proceedings of LREC 2018","author":"Tracey","key":"ref5"},{"article-title":"mslam: Massively multilingual joint pre-training for speech and text","year":"2022","author":"Bapna","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10937"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022791"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1392"},{"article-title":"Sentence-level multi-modal and language-agnostic representations","year":"2023","author":"Duquenne","key":"ref10"},{"article-title":"Building large monolingual dictionaries at the leipzig corpora collection: From 100 to 200 languages","volume-title":"International Conference on Language Resources and Evaluation","author":"Goldhahn","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.14618\/IDS-PUB-9021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.579"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-15"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.03.014"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383459"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-36"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-854"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/asru57964.2023.10389783"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11007"},{"article-title":"Listen, read, and identify: multimodal singing language identification of music","year":"2021","author":"Choi","key":"ref21"},{"article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of NAACL","author":"Devlin","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21327"},{"key":"ref28","article-title":"Google USM: scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023","journal-title":"CoRR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/slt54892.2023.10023141"},{"article-title":"Speechbrain: A general-purpose speech toolkit","year":"2021","author":"Ravanelli","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-143"},{"article-title":"Scaling speech technology to 1,000+ languages","year":"2023","author":"Vineel","key":"ref32"},{"article-title":"Ambernet: A compact end-to-end model for spoken language identification","year":"2022","author":"Jia","key":"ref33"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","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\/10448215.pdf?arnumber=10448215","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:43:15Z","timestamp":1722573795000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448215\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448215","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}