{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T20:22:02Z","timestamp":1751487722736},"reference-count":41,"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\/icassp48485.2024.10446286","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"13246-13250","source":"Crossref","is-referenced-by-count":3,"title":["Updated Corpora and Benchmarks for Long-Form Speech Recognition"],"prefix":"10.1109","author":[{"given":"Jennifer Drexler","family":"Fox","sequence":"first","affiliation":[{"name":"Rev.com"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Desh","family":"Raj","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Center for Language and Speech Processing,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Natalie","family":"Delworth","sequence":"additional","affiliation":[{"name":"Rev.com"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quinn","family":"McNamara","sequence":"additional","affiliation":[{"name":"Rev.com"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Corey","family":"Miller","sequence":"additional","affiliation":[{"name":"Rev.com"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mig\u00fcel","family":"Jett\u00e9","sequence":"additional","affiliation":[{"name":"Rev.com"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003913"},{"article-title":"Input length matters: Improving RNN-T and MWER training for long-form telephony speech recognition","year":"2021","author":"Lu","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-38"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3261662"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10096900"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2928"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1296"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096429"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003854"},{"key":"ref10","article-title":"The AMI meeting corpus: A pre-announcement","author":"Carletta","year":"2005","journal-title":"Machine Learning for Multimodal Interaction"},{"article-title":"SWITCH-BOARD: Telephone speech corpus for research and development","volume-title":"IEEE ICASSP","author":"Godfrey","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99579-3_21"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"article-title":"Sequence transduction with recurrent neural networks","volume-title":"ICML Representation Learning Workshop","author":"Graves","key":"ref15"},{"article-title":"Attention-based models for speech recognition","volume-title":"NIPS","author":"Chorowski","key":"ref16"},{"article-title":"Lhotse: A speech data representation library for the modern deep learning ecosystem","volume-title":"NeurIPS Data-centric AI Workshop","author":"\u017belasko","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683843"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639044"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-542"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-552"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10326"},{"article-title":"Random utterance concatenation based data augmentation for improving short-video speech recognition","volume-title":"InterSpeech","author":"Lin","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/slt48900.2021.9383518"},{"article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"ICML","author":"Radford","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054358"},{"article-title":"LSTM-LM with long-term history for first-pass decoding in conversational speech recognition","year":"2020","author":"Chen","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1813"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003788"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533796"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1915"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1915"},{"article-title":"The kaldi speech recognition toolkit","volume-title":"IEEE ASRU","author":"Povey","key":"ref33"},{"article-title":"Scaling speech technology to 1,000+ languages","year":"2023","author":"Pratap","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2017.7953075"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414941"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10340"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2258"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","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\/10446286.pdf?arnumber=10446286","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:44:08Z","timestamp":1722573848000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446286\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446286","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}