{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:14:46Z","timestamp":1776885286733,"version":"3.51.2"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10023234","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"1104-1111","source":"Crossref","is-referenced-by-count":28,"title":["On the Utility of Self-Supervised Models for Prosody-Related Tasks"],"prefix":"10.1109","author":[{"given":"Guan-Ting","family":"Lin","sequence":"first","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi-Luen","family":"Feng","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Ping","family":"Huang","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Tseng","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tzu-Han","family":"Lin","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen-An","family":"Li","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hung-yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nigel G.","family":"Ward","sequence":"additional","affiliation":[{"name":"University of Texas at El Paso,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.580"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101255"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1017\/9781316848265"},{"key":"ref6","first-page":"39","article-title":"Stepped intonation contours: A new field of complexity","volume-title":"Tackling the Complexity of Speech","author":"Niebuhr","year":"2015"},{"key":"ref7","first-page":"11134","article-title":"Learning de-identified representations of prosody from raw audio","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Weston","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-232"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1242"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746137"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref12","article-title":"What all do audio transformer models hear? probing acoustic representations for language delivery and its structure","author":"Shah","year":"2021","journal-title":"ar Xiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414321"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1228"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-349"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref19","first-page":"7414","article-title":"Unsupervised pre-training transfers well across languages","author":"Rivi\u00e8re","year":"2020","journal-title":"ICASSP"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref21","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"Baevski","year":"2020","journal-title":"ICLR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747490"},{"key":"ref23","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2022.3188113"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1455"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2663204.2663260"},{"key":"ref29","article-title":"Lib-riTTS: A corpus derived from librispeech for text-to-speech","volume":"abs\/1904.02882","author":"Zen","year":"2019","journal-title":"CoRR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-12122-9"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993176"},{"key":"ref32","volume-title":"Reaper: Robust epoch and pitch estima-tor","author":"Talkin","year":"2015"},{"key":"ref33","article-title":"Roberta: A ro-bustly optimized BERT pretraining approach","author":"Liu","year":"2019","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-755"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11174"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","location":"Doha, Qatar","start":{"date-parts":[[2023,1,9]]},"end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10023234.pdf?arnumber=10023234","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T08:36:47Z","timestamp":1707813407000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10023234\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10023234","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}