{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:52:45Z","timestamp":1753602765889,"version":"3.28.0"},"reference-count":61,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100002465","name":"Delta","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100002465","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389641","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-8","source":"Crossref","is-referenced-by-count":3,"title":["Espnet-Summ: Introducing a Novel Large Dataset, Toolkit, and a Cross-Corpora Evaluation of Speech Summarization Systems"],"prefix":"10.1109","author":[{"given":"Roshan","family":"Sharma","sequence":"first","affiliation":[{"name":"Carnegie Mellon University Pittsburgh,PA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William","family":"Chen","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University Pittsburgh,PA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takatomo","family":"Kano","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruchira","family":"Sharma","sequence":"additional","affiliation":[{"name":"University of Massachusetts Amherst"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siddhant","family":"Arora","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University Pittsburgh,PA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University Pittsburgh,PA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Atsunori","family":"Ogawa","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"Delcroix","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rita","family":"Singh","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University Pittsburgh,PA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhiksha","family":"Raj","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University Pittsburgh,PA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1336","article-title":"On Generative Spoken Language Modeling from Raw Audio","volume":"9","author":"Lakhotia","year":"2021","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2756440"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5743641"},{"key":"ref5","article-title":"Automatic speech summarisation: A scoping review","author":"Rezazadegan","year":"2020","journal-title":"arXiv preprint arXiv:2008.11897"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1659"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-945"},{"key":"ref8","first-page":"487","article-title":"Automatic summarization of medical conversations, a review","volume-title":"Actes de la Conf\u00e9rence sur le Traitement Automatique des Langues Naturelles (TALN) PFIA 2019. Volume III: RECITAL","author":"Espejel"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747320"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.496"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687977"},{"key":"ref12","article-title":"How2: A large-scale dataset for multimodal language understanding","author":"Sanabria","year":"2018","journal-title":"arXiv preprint arXiv:1811.00347"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.nlp4convai-1.11"},{"key":"ref14","first-page":"137","article-title":"The ami meeting corpus","volume-title":"Undefined, in Proceedings of Measuring Behavior 2005, 5th International Conference on Methods and Techniques in Behavioral Research","author":"McCowan"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198793"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1923"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.326"},{"key":"ref18","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022","journal-title":"arXiv preprint arXiv:2212.04356"},{"key":"ref19","article-title":"Speechstew: Simply mix all available speech recognition data to train one large neural network","author":"Chan","year":"2021","journal-title":"arXiv preprint arXiv:2104.02133"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"issue":"1","key":"ref21","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00311"},{"key":"ref24","article-title":"Lexical, prosodic, and syntactic cues for dialog acts","author":"Jurafsky","year":"1998","journal-title":"Discourse Relations and Discourse Markers"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1007"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094993"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1307"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-916"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.496"},{"issue":"1","key":"ref31","first-page":"34","article-title":"English gigaword","volume":"4","author":"Graff","year":"2003","journal-title":"Linguistic Data Consortium, Philadelphia"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d15-1044"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.653"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.474"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.19"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1683"},{"key":"ref37","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095019"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094993"},{"key":"ref40","article-title":"Xnor-former: Learning accurate approximations in long speech transformers","author":"Sharma","year":"2022","journal-title":"arXiv preprint arXiv:2210.16643"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"article-title":"Understanding and improving transformer from a multi-particle dynamic system point of view","volume-title":"ICLR 2020 Workshop on Integration of Deep Neural Models and Differential Equations","author":"Lu","key":"ref42"},{"key":"ref43","article-title":"Longformer: The long-document transformer","volume":"abs\/2004.05150","author":"Beltagy","year":"2020","journal-title":"CoRR"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.319"},{"article-title":"Chordmixer: A scalable neural attention model for sequences with different length","volume-title":"The Eleventh International Conference on Learning Representations","author":"Khalitov","key":"ref45"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.1987.1169544"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096977"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747674"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053512"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.34"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383615"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10039"},{"key":"ref54","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref55","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization","author":"Banerjee"},{"article-title":"Bertscore: Evaluating text generation with bert","volume-title":"International Conference on Learning Representations","author":"Zhang","key":"ref56"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"article-title":"The Kaldi speech recognition toolkit","volume-title":"IEEE 2011 Workshop on Automatic Speech Recognition and Understanding","author":"Povey","key":"ref60"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2680"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2023,12,16]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389641.pdf?arnumber=10389641","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:42:31Z","timestamp":1706028151000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389641\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389641","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}