{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:16:37Z","timestamp":1776885397889,"version":"3.51.2"},"reference-count":63,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888249","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["NEST: Self-supervised Fast Conformer as All-purpose Seasoning to Speech Processing Tasks"],"prefix":"10.1109","author":[{"given":"He","family":"Huang","sequence":"first","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taejin","family":"Park","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kunal","family":"Dhawan","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ivan","family":"Medennikov","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Krishna C.","family":"Puvvada","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nithin Rao","family":"Koluguri","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiqing","family":"Wang","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jagadeesh","family":"Balam","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boris","family":"Ginsburg","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref2","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-717"},{"key":"ref4","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"Baevski","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-391"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref7","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","volume-title":"ICML","author":"Chiu"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.570"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref11","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"ICML","author":"Baevski"},{"key":"ref12","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-143"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref16","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389701"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref19","article-title":"Seamless: Multilingual expressive and streaming speech translation","author":"Barrault","year":"2023"},{"key":"ref20","first-page":"28 492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2294"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref24","first-page":"69","article-title":"The fisher corpus: A resource for the next generations of speech-to-text","volume-title":"LREC","volume":"4","author":"Cieri"},{"key":"ref25","article-title":"Switchboard-1 release 2","author":"John"},{"key":"ref26","article-title":"Csr-i (wsj0) complete","author":"Garofolo"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1525"},{"key":"ref28","article-title":"The people\u2019s speech: A large-scale diverse english speech recognition dataset for commercial usage","author":"Galvez","year":"2021"},{"key":"ref29","article-title":"Musan: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref30","article-title":"Freesound datasets: a platform for the creation of open audio datasets","volume-title":"ISMIR","author":"Fonseca"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3162080"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3233237"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-991"},{"key":"ref37","article-title":"Sortformer: Seamless integration of speaker diarization and asr by bridging timestamps and tokens","author":"Park","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446861"},{"key":"ref39","first-page":"4211","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"LREC","author":"Ardila"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1860"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054626"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref44","article-title":"Nemo english fastconformer-rnnt asr model"},{"key":"ref45","article-title":"Megatron multilingual translation model"},{"key":"ref46","article-title":"mexpresso (multilingual expresso)"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023141"},{"key":"ref48","article-title":"The ami corpus"},{"key":"ref49","article-title":"The icsi meeting corpus"},{"key":"ref50","article-title":"Third dihard challenge evaluation plan","author":"Ryant","year":"2020"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2337"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1397"},{"key":"ref53","article-title":"Kaldi x-vector recipe v2"},{"key":"ref54","article-title":"2000 nist speaker recognition evaluation","author":"Przybocki"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(99)00080-1"},{"key":"ref56","article-title":"Nist speaker recognition evaluation (sre)"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2023-16"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.588"},{"key":"ref59","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":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747674"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW62465.2024.10626364"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747047"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-461"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888249.pdf?arnumber=10888249","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:49Z","timestamp":1774416169000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888249\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888249","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}