{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:27:02Z","timestamp":1775230022578,"version":"3.50.1"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447120","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10991-10995","source":"Crossref","is-referenced-by-count":26,"title":["Libriheavy: A 50,000 Hours ASR Corpus with Punctuation Casing and Context"],"prefix":"10.1109","author":[{"given":"Wei","family":"Kang","sequence":"first","affiliation":[{"name":"Xiaomi Corp.,Beijing,China"}]},{"given":"Xiaoyu","family":"Yang","sequence":"additional","affiliation":[{"name":"Xiaomi Corp.,Beijing,China"}]},{"given":"Zengwei","family":"Yao","sequence":"additional","affiliation":[{"name":"Xiaomi Corp.,Beijing,China"}]},{"given":"Fangjun","family":"Kuang","sequence":"additional","affiliation":[{"name":"Xiaomi Corp.,Beijing,China"}]},{"given":"Yifan","family":"Yang","sequence":"additional","affiliation":[{"name":"Xiaomi Corp.,Beijing,China"}]},{"given":"Liyong","family":"Guo","sequence":"additional","affiliation":[{"name":"Xiaomi Corp.,Beijing,China"}]},{"given":"Long","family":"Lin","sequence":"additional","affiliation":[{"name":"Xiaomi Corp.,Beijing,China"}]},{"given":"Daniel","family":"Povey","sequence":"additional","affiliation":[{"name":"Xiaomi Corp.,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref2","article-title":"Speech recognition with deep recurrent neural networks","volume-title":"Proc. ICASSP","author":"Mohamed"},{"key":"ref3","article-title":"Listen, attend and spell","volume-title":"Proc. ICASSP","author":"Chan"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref6","article-title":"Switchboard-1 release 2 ldc97s62","author":"Godfrey","year":"1993"},{"key":"ref7","article-title":"Fisher english training speech part 1 transcripts ldc2004t19","author":"Cieri","year":"2004"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref10","article-title":"The people\u2019s speech: A large-scale diverse english speech recognition dataset for commercial usage","author":"Galvez","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688079"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095204"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref15","article-title":"Lhotse: a speech data representation library for the modern deep learning ecosystem","author":"\u017belasko","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1217856.1217858"},{"key":"ref17","article-title":"Binary codes capable of correcting deletions, insertions, and reversals","volume-title":"Soviet physics doklady","author":"Levenshtein","year":"1966"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1983"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref24","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"Computer Science"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054419"},{"key":"ref27","author":"Yao","year":"2023","journal-title":"Zip-former: A faster and better encoder for automatic speech recognition"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094567"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447120.pdf?arnumber=10447120","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:29:59Z","timestamp":1722576599000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447120\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447120","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}