{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T15:42:18Z","timestamp":1725810138956},"reference-count":26,"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\/icassp48485.2024.10448309","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"13366-13370","source":"Crossref","is-referenced-by-count":0,"title":["Investigating End-to-End ASR Architectures for Long Form Audio Transcription"],"prefix":"10.1109","author":[{"given":"Nithin Rao","family":"Koluguri","sequence":"first","affiliation":[]},{"given":"Samuel","family":"Kriman","sequence":"additional","affiliation":[]},{"given":"Georgy","family":"Zelenfroind","sequence":"additional","affiliation":[]},{"given":"Somshubra","family":"Majumdar","sequence":"additional","affiliation":[]},{"given":"Dima","family":"Rekesh","sequence":"additional","affiliation":[]},{"given":"Vahid","family":"Noroozi","sequence":"additional","affiliation":[]},{"given":"Jagadeesh","family":"Balam","sequence":"additional","affiliation":[]},{"given":"Boris","family":"Ginsburg","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095355"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-38"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003854"},{"year":"2022","key":"ref5","article-title":"Streaming \/ Buffered ASR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003913"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413899"},{"journal-title":"ICLR","article-title":"Dual-mode ASR: Unify and improve streaming ASR with full-context modeling","year":"2021","author":"Yu","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1983"},{"year":"2023","key":"ref10","article-title":"Cache-aware streaming conformer"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053889"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2059"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389701"},{"author":"Harper","key":"ref14","article-title":"NeMo: a toolkit for Conversational AI and Large Language Models"},{"journal-title":"ICLR","article-title":"Wav2letter: an end-to-end convnet-based speech recognition system","year":"2016","author":"Collobert","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1819"},{"journal-title":"ICML","article-title":"Sequence transduction with recurrent neural networks","year":"2012","author":"Graves","key":"ref17"},{"journal-title":"ICLR","article-title":"Searching for activation functions","year":"2017","author":"Ramachandran","key":"ref18"},{"article-title":"Citrinet: Closing the gap between non-autoregressive and autoregressive end-to-end models for automatic speech recognition","year":"2021","author":"Majumdar","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99579-3_21"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1915"},{"year":"2022","key":"ref22","article-title":"speech-datasets"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctv1g4rvf6.8"},{"journal-title":"ICML","article-title":"Robust speech recognition via large-scale weak supervision","year":"2023","author":"Radford","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268935"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"}],"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\/10448309.pdf?arnumber=10448309","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:52:07Z","timestamp":1722660727000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448309\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448309","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}
