{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,18]],"date-time":"2025-01-18T05:06:47Z","timestamp":1737176807183,"version":"3.33.0"},"reference-count":37,"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\/slt61566.2024.10832230","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"110-117","source":"Crossref","is-referenced-by-count":0,"title":["Transducer Consistency Regularization For Speech to Text Applications"],"prefix":"10.1109","author":[{"given":"Cindy","family":"Tseng","sequence":"first","affiliation":[{"name":"Samsung Research America,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun","family":"Tang","sequence":"additional","affiliation":[{"name":"Samsung Research America,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vijendra Raj","family":"Apsingekar","sequence":"additional","affiliation":[{"name":"Samsung Research America,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1211.3711"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"article-title":"Transformer-transducer: End-to-end speech recognition with self-attention","year":"2019","author":"Yeh","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003854"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2846"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2079"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414560"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.4"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10953"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.695"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389791"},{"key":"ref13","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020","journal-title":"ArXiv"},{"key":"ref14","article-title":"R-drop: Regularized dropout for neural networks","author":"Liang","year":"2021","journal-title":"Neural Information Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858821"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094595"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.14"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref21","first-page":"6256","article-title":"Unsupervised data augmentation for consistency training","volume":"33","author":"Xie","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10462"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052940"},{"article-title":"Dual-mode asr: Unify and improve streaming asr with full-context modeling","volume-title":"International Conference on Learning Representations","author":"Yu","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413905"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10340"},{"article-title":"A comparison of label-synchronous and frame-synchronous end-to-end models for speech recognition","year":"2020","author":"Dong","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref29","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref31","first-page":"2012","article-title":"Must-c: a multilingual speech translation corpus","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Di Gangi"},{"article-title":"Zipformer: A faster and better encoder for automatic speech recognition","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yao","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414594"},{"key":"ref35","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint arXiv:1711.05101"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref37","article-title":"Nemo: a toolkit for building ai applications using neural modules","author":"Kuchaiev","year":"2019","journal-title":"arXiv preprint arXiv:1909.09577"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2024,12,2]]},"location":"Macao","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\/10832230.pdf?arnumber=10832230","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:44:10Z","timestamp":1737099850000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832230\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832230","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}