{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,18]],"date-time":"2025-01-18T05:07:37Z","timestamp":1737176857257,"version":"3.33.0"},"reference-count":39,"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\/slt61566.2024.10832171","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"232-239","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Unified Streaming and Non-Streaming ASR Through Curriculum Learning With Easy-To-Hard Tasks"],"prefix":"10.1109","author":[{"given":"Yuting","family":"Yang","sequence":"first","affiliation":[{"name":"NetEase Yidun AI Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuke","family":"Li","sequence":"additional","affiliation":[{"name":"NetEase Yidun AI Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lifeng","family":"Zhou","sequence":"additional","affiliation":[{"name":"NetEase Yidun AI Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Binbin","family":"Du","sequence":"additional","affiliation":[{"name":"NetEase Yidun AI Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoqi","family":"Zhu","sequence":"additional","affiliation":[{"name":"NetEase Yidun AI Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Unified streaming and non-streaming two-pass end-to-end model for speech recognition","author":"Zhang","year":"2020","journal-title":"arXiv preprint arXiv:2012.05481"},{"key":"ref2","article-title":"Universal asr: Unifying streaming and non-streaming asr using a single encoder-decoder model","author":"Gao","year":"2020","journal-title":"arXiv preprint arXiv:2010.14099"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414607"},{"key":"ref4","article-title":"Dual-mode asr: Unify and improve streaming asr with full-context modeling","author":"Yu","year":"2021","journal-title":"ICLR"},{"key":"ref5","article-title":"Transformer transducer: One model unifying streaming and non-streaming speech recognition","author":"Tripathi","year":"2020","journal-title":"arXiv preprint arXiv:2010.03192"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096154"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413692"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054476"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682954"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003749"},{"key":"ref11","article-title":"U2++: Unified two-pass bidirectional end-to-end model for speech recognition","author":"Wu","year":"2021","journal-title":"arXiv preprint arXiv:2106.05642"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-831"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1119"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.41"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.542"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_7"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.223"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389760"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1828"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1630"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10046"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref28","article-title":"Aishell-2: Transforming mandarin asr research into industrial scale","author":"Du","year":"2018","journal-title":"arXiv preprint arXiv:1808.10583"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1983"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"issue":"1","key":"ref32","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"The journal of machine learning research"},{"key":"ref33","article-title":"When does label smoothing help?","volume":"32","author":"M\u00fcller","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref34","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint arXiv:1412.6980"},{"key":"ref35","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":"ref36","article-title":"First-pass large vocabulary continuous speech recognition using bi-directional recurrent dnns","author":"Hannun","year":"2014","journal-title":"arXiv preprint arXiv:1408.2873"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1898"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1887"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097012"}],"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\/10832171.pdf?arnumber=10832171","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:50:11Z","timestamp":1737100211000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832171\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832171","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}