{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:59:40Z","timestamp":1776884380483,"version":"3.51.2"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100002465","name":"Delta","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100002465","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434746","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["Geolocation-Aware Robust Spoken Language Identification"],"prefix":"10.1109","author":[{"given":"Qingzheng","family":"Wang","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Hye-Jin","family":"Shim","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Jiancheng","family":"Sun","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]}],"member":"263","reference":[{"issue":"97","key":"ref1","first-page":"1","article-title":"Scaling speech technology to 1,000+ languages","volume":"25","author":"Pratap","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.570"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-143"},{"key":"ref4","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1194"},{"key":"ref6","article-title":"Google USM: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv:2303.01037"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383459"},{"key":"ref8","article-title":"Seamless: Multilingual expressive and streaming speech translation","author":"Barrault","year":"2023","journal-title":"arXiv preprint arXiv:2312.05187"},{"key":"ref9","article-title":"SeamlessM4T: Massively multilingual & multimodal machine translation","author":"Barrault","year":"2023","journal-title":"arXiv preprint arXiv:2308.11596"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-1062"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3201445"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1157"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2254"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2002"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-1013"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023141"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.286"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.63317\/5q5xs2oxi7sb"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383538"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462550"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414594"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052964"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-2377"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-911"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095326"},{"key":"ref26","article-title":"CA-SSLR: Condition-aware self-supervised learning representation for generalized speech processing","volume-title":"Proc. NeurIPS","author":"Lu"},{"key":"ref27","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeurIPS","volume":"33","author":"Baevski"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2019.2938758"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1502.03167"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref37","article-title":"The SpeakIn system for VoxCeleb speaker recognition challenge 2021","author":"Zhao","year":"2021","journal-title":"arXiv preprint arXiv:2109.01989"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1345"},{"key":"ref39","volume-title":"Glottolog 5.2","author":"Hammarstr\u00f6m","year":"2025"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11004-009-9257-x"},{"key":"ref41","first-page":"16","article-title":"Speech recognition and keyword spotting for low-resource languages: Babel project research at cued","volume-title":"Proc. SLTU","author":"Gales"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref43","volume-title":"Interspeech 2025 ML-SUPERB 2.0 challenge","author":"Chen","year":"2025"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref45","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR (Poster)","author":"Kingma"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10455"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2310"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434746.pdf?arnumber=11434746","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:59:13Z","timestamp":1775192353000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434746\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434746","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}