{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:23:40Z","timestamp":1775229820338,"version":"3.50.1"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832349","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"224-231","source":"Crossref","is-referenced-by-count":1,"title":["Augmenting Automatic Speech Recognition Models With Disfluency Detection"],"prefix":"10.1109","author":[{"given":"Robin","family":"Amann","sequence":"first","affiliation":[{"name":"Karlsruhe Institute of Technology,Germany"}]},{"given":"Zhaolin","family":"Li","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology,Germany"}]},{"given":"Barbara","family":"Bruno","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology,Germany"}]},{"given":"Jan","family":"Niehues","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology,Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60276-5_27"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580788"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/00222194221095265"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1887"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581224"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.60"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-351"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.286"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746067"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2157"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3110146"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094620"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-281"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389771"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095555"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2246"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/SLaTE.2023-20"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5210\/dad.2022.201"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-204"},{"key":"ref20","article-title":"Enhancing ASR for stuttered speech with limited data using detect and pass","author":"Shonibare","year":"2022"},{"key":"ref21","first-page":"539","article-title":"Towards hierarchical spoken language disfluency modeling","volume-title":"Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Lian"},{"key":"ref22","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref23","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref25","article-title":"SpeechBrain: A general-purpose speech toolkit","author":"Ravanelli","year":"2021"},{"key":"ref26","article-title":"Flashlight: Enabling innovation in tools for machine learning","author":"Kahn","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v031.i07"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832349.pdf?arnumber=10832349","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:11:34Z","timestamp":1737101494000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832349\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832349","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}