{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T15:58:14Z","timestamp":1777391894630,"version":"3.51.4"},"reference-count":109,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3389631","type":"journal-article","created":{"date-parts":[[2024,4,16]],"date-time":"2024-04-16T17:28:20Z","timestamp":1713288500000},"page":"2884-2899","source":"Crossref","is-referenced-by-count":41,"title":["A Large-Scale Evaluation of Speech Foundation Models"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5503-9410","authenticated-orcid":false,"given":"Shu-wen","family":"Yang","sequence":"first","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1690-2610","authenticated-orcid":false,"given":"Heng-Jui","family":"Chang","sequence":"additional","affiliation":[{"name":"CSAIL, MIT, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1238-8017","authenticated-orcid":false,"given":"Zili","family":"Huang","sequence":"additional","affiliation":[{"name":"CLSP, JHU, Baltimore, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2502-3992","authenticated-orcid":false,"given":"Andy T.","family":"Liu","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2343-8596","authenticated-orcid":false,"given":"Cheng-I","family":"Lai","sequence":"additional","affiliation":[{"name":"CSAIL, MIT, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7166-5534","authenticated-orcid":false,"given":"Haibin","family":"Wu","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9050-8304","authenticated-orcid":false,"given":"Jiatong","family":"Shi","sequence":"additional","affiliation":[{"name":"LTI, CMU, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5221-5412","authenticated-orcid":false,"given":"Xuankai","family":"Chang","sequence":"additional","affiliation":[{"name":"LTI, CMU, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2574-1610","authenticated-orcid":false,"given":"Hsiang-Sheng","family":"Tsai","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3172-3335","authenticated-orcid":false,"given":"Wen-Chin","family":"Huang","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Nagoya, Aichi, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1993-6161","authenticated-orcid":false,"given":"Tzu-hsun","family":"Feng","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8183-3781","authenticated-orcid":false,"given":"Po-Han","family":"Chi","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9054-1596","authenticated-orcid":false,"given":"Yist Y.","family":"Lin","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1723-5063","authenticated-orcid":false,"given":"Yung-Sung","family":"Chuang","sequence":"additional","affiliation":[{"name":"CSAIL, MIT, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tzu-Hsien","family":"Huang","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4928-6257","authenticated-orcid":false,"given":"Wei-Cheng","family":"Tseng","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kushal","family":"Lakhotia","sequence":"additional","affiliation":[{"name":"FAIR, Menlo Park, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0656-9874","authenticated-orcid":false,"given":"Shang-Wen","family":"Li","sequence":"additional","affiliation":[{"name":"Amazon AI, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdelrahman","family":"Mohamed","sequence":"additional","affiliation":[{"name":"FAIR, Menlo Park, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5970-8631","authenticated-orcid":false,"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"LTI, CMU, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9654-5747","authenticated-orcid":false,"given":"Hung-yi","family":"Lee","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"ref2","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9053176"},{"key":"ref9","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1873"},{"key":"ref11","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref12","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Int. Adv. Conf. Neural Inf. Process. Syst.","author":"Baevski","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref17","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Baevski"},{"key":"ref18","article-title":"The zero resource speech benchmark 2021: Metrics and baselines for unsupervised spoken language modeling","volume-title":"Proc. NeuRIPS Workshop Self-Supervised Learn. Speech Audio Process.","author":"Nguyen","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-556"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.580"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-63"},{"key":"ref24","first-page":"5210","article-title":"Autovc: Zero-shot voice style transfer with only autoencoder loss","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qian","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746137"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.496"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747197"},{"key":"ref29","article-title":"A fine-tuned wav2vec 2.0\/hubert benchmark for speech emotion recognition, speaker verification and spoken language understanding","author":"Wang","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023141"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10007"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022770"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1316"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref36","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1800"},{"key":"ref38","article-title":"On the transferability of whisper-based representations for in-the-wild cross-task downstream speech applications","author":"Chemudupati","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref41","article-title":"Unified hypersphere embedding for speaker recognition","author":"Hajibabaei","year":"2018"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref43","first-page":"3097","article-title":"Emotion identification from raw speech signals using DDNs","volume-title":"Proc. Annu. Conf. Int. Speech Commun. Assoc.","author":"Sarma","year":"2018"},{"key":"ref44","article-title":"Speech commands: A. public dataset for single-word speech recognition","volume-title":"arXiv:1804.03209","author":"Warden","year":"2018"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87802-3_69"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414900"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-740"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-993"},{"key":"ref49","article-title":"Librimix: An open-source dataset for generalizable speech separation","author":"Cosentino","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179090"},{"key":"ref51","article-title":"GTTS-EHU systems for QUESST at MediaEval 2014","volume-title":"Proc. MediaEval 2014 Workshop","author":"Rodrguez-Fuentes","year":"2014"},{"key":"ref52","article-title":"Snips voice platform: An embedded spoken language understanding system for private-by-design voice interfaces","author":"Coucke","year":"2018"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414922"},{"key":"ref54","article-title":"Bert for joint intent classification and slot filling","author":"Chen","year":"2019"},{"key":"ref55","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proc. 12th Lang. Resour. Eval. Conf.","author":"Ardila","year":"2020"},{"key":"ref56","article-title":"Santa barbara corpus of spoken american english","author":"Du Bois","year":"2000"},{"key":"ref57","first-page":"2247","article-title":"CoVoST 2: A. massively multilingual speech-to-text translation corpus","volume-title":"Proc. Interspeech","author":"Wang","year":"2020"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.68"},{"key":"ref59","first-page":"80","article-title":"Voice Conversion Challenge 2020 - Intra-lingual semi-parallel and cross-lingual voice conversion","volume-title":"Proc. Joint Workshop BC VCC","author":"Zhao","year":"2020"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/VCCBC.2020-16"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709856"},{"key":"ref62","first-page":"936","article-title":"Cmgan: Conformer-based metric-gan for monaural speech enhancement","volume-title":"Proc. Interspeech","author":"Abdulatif","year":"2022"},{"key":"ref63","article-title":"An efficient encoder-decoder architecture with top-down attention for speech separation","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Li","year":"2022"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.6028\/nist.ir.4930"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref67","article-title":"GTTS-EHU systems for QUEST at MediaEval 2014","author":"Rodriguez-Fuentes","year":"2014","journal-title":"Work. Notes Proc. MediaEval Workshop"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v031.i07"},{"key":"ref69","article-title":"MUSAN: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2822810"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2396"},{"key":"ref75","article-title":"Towards semi-supervised semantics understanding from speech","author":"Lai","year":"2020"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-31372-2_4"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746430"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1190"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref81","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Int. Adv. Conf. Neural Inf. Process. Syst.","author":"Kong","year":"2020"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747236"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1228"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-349"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/slt48900.2021.9383575"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747490"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053176"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054548"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094726"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022552"},{"key":"ref95","article-title":"Self-supervised representation learning for speech using visual grounding and masked language modeling","author":"Peng","year":"2022"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10269"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1390"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1213"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747077"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1087"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref102","first-page":"18003","article-title":"ContentVec: An improved self-supervised speech representation by disentangling speakers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qian","year":"2022"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096149"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.115546"},{"key":"ref105","first-page":"279","article-title":"The expected performance curve: A new assessment measure for person authentication","volume-title":"Proc. Speaker Lang. Recognit. Workshop","author":"Bengio","year":"2004"},{"key":"ref106","first-page":"388","article-title":"Statistical significance tests for machine translation evaluation","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Koehn","year":"2004"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00277"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1388"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10502279.pdf?arnumber=10502279","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,5]],"date-time":"2024-06-05T18:00:28Z","timestamp":1717610428000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10502279\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":109,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3389631","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}