{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:05:31Z","timestamp":1775199931795,"version":"3.50.1"},"reference-count":51,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434691","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["LCS-CTC: Leveraging Soft Alignments to Enhance Phonetic Transcription Robustness"],"prefix":"10.1109","author":[{"given":"Zongli","family":"Ye","sequence":"first","affiliation":[{"name":"Zhejiang University"}]},{"given":"Jiachen","family":"Lian","sequence":"additional","affiliation":[{"name":"UC Berkeley"}]},{"given":"Akshaj","family":"Gupta","sequence":"additional","affiliation":[{"name":"UC Berkeley"}]},{"given":"Xuanru","family":"Zhou","sequence":"additional","affiliation":[{"name":"Zhejiang University"}]},{"given":"Haodong","family":"Li","sequence":"additional","affiliation":[{"name":"SUSTech"}]},{"given":"Krish","family":"Patel","sequence":"additional","affiliation":[{"name":"UC Berkeley"}]},{"given":"Hwi Joo","family":"Park","sequence":"additional","affiliation":[{"name":"UC Berkeley"}]},{"given":"Dingkun","family":"Zhou","sequence":"additional","affiliation":[{"name":"SCUT"}]},{"given":"Chenxu","family":"Guo","sequence":"additional","affiliation":[{"name":"Zhejiang University"}]},{"given":"Shuhe","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University"}]},{"given":"Sam","family":"Wang","sequence":"additional","affiliation":[{"name":"UC Berkeley"}]},{"given":"Iris","family":"Zhou","sequence":"additional","affiliation":[{"name":"UC Berkeley"}]},{"given":"Cheol Jun","family":"Cho","sequence":"additional","affiliation":[{"name":"UC Berkeley"}]},{"given":"Zoe","family":"Ezzes","sequence":"additional","affiliation":[{"name":"IUCSF"}]},{"given":"Jet M.J.","family":"Vonk","sequence":"additional","affiliation":[{"name":"IUCSF"}]},{"given":"Brittany T.","family":"Morin","sequence":"additional","affiliation":[{"name":"IUCSF"}]},{"given":"Rian","family":"Bogley","sequence":"additional","affiliation":[{"name":"IUCSF"}]},{"given":"Lisa","family":"Wauters","sequence":"additional","affiliation":[{"name":"IUCSF"}]},{"given":"Zachary A.","family":"Miller","sequence":"additional","affiliation":[{"name":"IUCSF"}]},{"given":"Maria Luisa","family":"Gorno-Tempini","sequence":"additional","affiliation":[{"name":"IUCSF"}]},{"given":"Gopala","family":"Anumanchipalli","sequence":"additional","affiliation":[{"name":"UC Berkeley"}]}],"member":"263","reference":[{"key":"ref1","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning.","author":"Radford"},{"key":"ref2","article-title":"Google usm: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv:2303.01037"},{"issue":"97","key":"ref3","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":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2294"},{"key":"ref5","article-title":"Parakeet-rnnt-1.1b: A fastconformer transducer model for english asr","author":"NeMo"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.557"},{"key":"ref7","first-page":"032","article-title":"Automatic pronunciation error detection: an acoustic-phonetic approach","volume-title":"InSTIL\/ICALL 2004 Symposium on Computer Assisted Learning","volume":"2004","author":"Truong"},{"key":"ref8","article-title":"Language-independent methods for computer-assisted pronunciation training","author":"Lee","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1044\/2024_AJSLP-23-00208"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1080\/02687038.2023.2244728"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1080\/02687039808249565"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1044\/2021_JSLHR-21-00484"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1080\/02687038.2023.2171261"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3230"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2025.3579972"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1855"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832222"},{"key":"ref18","article-title":"Time and tokens: Benchmarking end-to-end speech dysfluency detection","author":"Zhou","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.132"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref21","article-title":"Attention-based models for speech recognition","volume":"28","author":"Chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"Why does ctc result in peaky behavior?","author":"Zeyer","year":"2021","journal-title":"arXiv preprint arXiv:2105.14849"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658996"},{"key":"ref24","article-title":"Bayes risk ctc: Controllable ctc alignment in sequence-to-sequence tasks","author":"Tian","year":"2023","journal-title":"ICLR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446111"},{"key":"ref26","article-title":"Cr-ctc: Consistency regularization on ctc for improved speech recognition","author":"Yao","year":"2025","journal-title":"ICLR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389771"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-long.32"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-2496"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/322033.322044"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0b013e31821103e6"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-2658"},{"key":"ref34","article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019","journal-title":"The Centre for Speech Technology Research (CSTR)"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref36","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref38","article-title":"Model card addendum: Claude 3.5 haiku and upgraded claude 3.5 sonnet","year":"2024","journal-title":"Anthropic"},{"key":"ref39","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"International Conference on Machine Learning.","author":"Kim"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-2446"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2024.3497655"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746112"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747085"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-08359-z"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-2417"},{"key":"ref48","article-title":"K-function: Joint pronunciation transcription and feedback for evaluating kids language function","author":"Li","year":"2025","journal-title":"arXiv preprint arXiv:2507.03043"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2024.3497655"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11233"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096401"}],"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\/11434691.pdf?arnumber=11434691","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:58:23Z","timestamp":1775192303000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434691\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434691","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}