{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:26:55Z","timestamp":1775230015352,"version":"3.50.1"},"reference-count":38,"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\/asru57964.2023.10389771","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":8,"title":["Unconstrained Dysfluency Modeling for Dysfluent Speech Transcription and Detection"],"prefix":"10.1109","author":[{"given":"Jiachen","family":"Lian","sequence":"first","affiliation":[{"name":"UC Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carly","family":"Feng","sequence":"additional","affiliation":[{"name":"Harvard University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naasir","family":"Farooqi","sequence":"additional","affiliation":[{"name":"UC Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steve","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anshul","family":"Kashyap","sequence":"additional","affiliation":[{"name":"UC Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheol Jun","family":"Cho","sequence":"additional","affiliation":[{"name":"UC Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Wu","sequence":"additional","affiliation":[{"name":"UC Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robbie","family":"Netzorg","sequence":"additional","affiliation":[{"name":"UC Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tingle","family":"Li","sequence":"additional","affiliation":[{"name":"UC Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gopala Krishna","family":"Anumanchipalli","sequence":"additional","affiliation":[{"name":"UC Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/14651858.CD000425.pub4"},{"key":"ref2","article-title":"Dyslexia, speech and language: a practitioner\u2019s handbook","author":"Snowling","year":"2013","journal-title":"John Wiley & Sons"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2012.6349744"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.09.001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1887"},{"key":"ref6","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref7","article-title":"Av-data2vec: Self-supervised learning of audio-visual speech representations with contextualized target representations","author":"Lian","year":"2023","journal-title":"arXiv preprint arXiv:2302.06419"},{"key":"ref8","article-title":"Google usm: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv:2303.01037"},{"key":"ref9","article-title":"Scaling speech technology to 1,000+ languages","author":"Pratap","year":"2023","journal-title":"arXiv preprint arXiv:2305.13516"},{"key":"ref10","article-title":"Scaling laws for generative mixed-modal language models","volume-title":"International Conference on Machine Learning","author":"Aghajanyan"},{"key":"ref11","article-title":"Wavlm-ctc-hugginface"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-78"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3110146"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/WOCCI.2017-1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101052"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746638"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-204"},{"key":"ref18","article-title":"Enhancing asr for stuttered speech with limited data using detect and pass","author":"Shonibare","year":"2022","journal-title":"arXiv preprint arXiv:2202.05396"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref22","article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019","journal-title":"University of Edinburgh. The Centre for Speech Technology Research (CSTR)"},{"key":"ref23","article-title":"Scaling speech technology to 1,000+ languages","author":"Pratap","year":"2023","journal-title":"arXiv preprint arXiv:2305.13516"},{"key":"ref24","article-title":"Cmu phoneme dictionary"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022827"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747272"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11225"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3290423"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319366"},{"key":"ref30","article-title":"Silero vad: pre-trained enterprise-grade voice activity detector (vad), number detector and language classifier","author":"Team","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60276-5_27"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11233"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096401"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096796"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2316"},{"key":"ref37","article-title":"Listen, think, and understand","author":"Gong","year":"2023","journal-title":"arXiv preprint arXiv:2305.10790"},{"key":"ref38","article-title":"Audiopalm: A large language model that can speak and listen","author":"Rubenstein","year":"2023","journal-title":"arXiv preprint arXiv:2306.12925"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,12,16]]},"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\/10389771.pdf?arnumber=10389771","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:42:47Z","timestamp":1706028167000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389771\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389771","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}