{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:41:24Z","timestamp":1777657284624,"version":"3.51.4"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095710","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":27,"title":["Speechlmscore: Evaluating Speech Generation Using Speech Language Model"],"prefix":"10.1109","author":[{"given":"Soumi","family":"Maiti","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Peng","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takaaki","family":"Saeki","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"27263","article-title":"Bartscore: Evaluating generated text as text generation","volume":"34","author":"yuan","year":"2021","journal-title":"Proc NeurIPS"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref12","article-title":"Bertscore: Evaluating text generation with bert","author":"zhang","year":"2019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-317"},{"key":"ref15","article-title":"Discretalk: Text-to-speech as a machine translation problem","author":"hayashi","year":"2020"},{"key":"ref37","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref14","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc ACL"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref31","article-title":"The blizzard challenge 2008","author":"king","year":"2008"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1053"},{"key":"ref33","article-title":"The blizzard challenge 2013–indian language task","author":"prahallad","year":"2013"},{"key":"ref10","article-title":"Audiolm: a language modeling approach to audio generation","author":"borsos","year":"2022"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.21437\/Blizzard.2009-1","article-title":"The blizzard challenge 2009","author":"king","year":"2009"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225953"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3038"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/13.1.25"},{"key":"ref16","article-title":"AutoMOS: Learning a non-intrusive assessor of naturalness-of-speech","author":"patton","year":"2016"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2052247"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-407"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref24","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref23","first-page":"100","article-title":"Algorithm as 136: A k-means clustering algorithm","volume":"28","author":"hartigan","year":"1979","journal-title":"Journal of the Royal Statistical Society Series C (Applied Statistics)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1066"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383461"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10633"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref22","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/2792745.2792775"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2014.80"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/VCC_BC.2020-14"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053512"},{"key":"ref8","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":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-970"},{"key":"ref9","article-title":"Text-free prosody-aware generative spoken language modeling","author":"kharitonov","year":"2021"},{"key":"ref4","article-title":"SQuId: Measuring speech naturalness in many languages","author":"sellam","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746395"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414878"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.2307\/1422689"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095710.pdf?arnumber=10095710","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T22:10:56Z","timestamp":1729375856000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095710\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095710","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}