{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:08:46Z","timestamp":1775200126338,"version":"3.50.1"},"reference-count":23,"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\/asru65441.2025.11434738","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["WST: Weakly Supervised Transducer for Automatic Speech Recognition"],"prefix":"10.1109","author":[{"given":"Dongji","family":"Gao","sequence":"first","affiliation":[{"name":"Johns Hopkins University"}]},{"given":"Chenda","family":"Liao","sequence":"additional","affiliation":[{"name":"Microsoft"}]},{"given":"Changliang","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft"}]},{"given":"Matthew","family":"Wiesner","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}]},{"given":"Leibny Paola","family":"Garcia","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}]},{"given":"Daniel","family":"Povey","sequence":"additional","affiliation":[{"name":"Xiaomi"}]},{"given":"Sanjeev","family":"Khudanpur","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}]},{"given":"Jian","family":"Wu","sequence":"additional","affiliation":[{"name":"Microsoft"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref3","article-title":"Sequence transduction with recurrent neural networks","author":"Graves","year":"2012","journal-title":"ICML"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2846"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2638"},{"key":"ref8","article-title":"Transformer in action: A comparative study of transformer-based acoustic models for large scale speech recognition applications","volume-title":"ICASSP.","author":"Wang","year":"2020"},{"key":"ref9","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"ICML.","author":"Radford","year":"2023"},{"key":"ref10","article-title":"Scaling speech technology to 1,000+ languages","author":"Pratap","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389676"},{"key":"ref12","article-title":"W-ctc: a connectionist temporal classification loss with wild cards","author":"Cai","year":"2022","journal-title":"ICLR"},{"key":"ref13","article-title":"Star temporal classification: Sequence classification with partially labeled data","author":"Pratap","year":"2022","journal-title":"NeurIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2258"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389684"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096679"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832209"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3306709"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2016-595"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054419"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref22","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"}],"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\/11434738.pdf?arnumber=11434738","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:59:06Z","timestamp":1775192346000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434738\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434738","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}