{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:25:16Z","timestamp":1775229916293,"version":"3.50.1"},"reference-count":40,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095773","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":3,"title":["Modelling Low-Resource Accents Without Accent-Specific TTS Frontend"],"prefix":"10.1109","author":[{"given":"Georgi","family":"Tinchev","sequence":"first","affiliation":[{"name":"Amazon Research,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marta","family":"Czarnowska","sequence":"additional","affiliation":[{"name":"Amazon Research,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kamil","family":"Deja","sequence":"additional","affiliation":[{"name":"Warsaw University of Technology,Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kayoko","family":"Yanagisawa","sequence":"additional","affiliation":[{"name":"Amazon Research,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marius","family":"Cotescu","sequence":"additional","affiliation":[{"name":"Amazon Research,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1038"},{"key":"ref35","article-title":"Method for the subjective assessment of intermediate sound quality (MUSHRA)","author":"recommendation","year":"2001","journal-title":"ITU BS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178767"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-242"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.11.004"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022506"},{"key":"ref14","article-title":"Spoken language conversion with accent morphing","author":"huckvale","year":"2007"},{"key":"ref36","article-title":"GradTTS: A diffusion probabilistic model for TTS","author":"popov","year":"2021","journal-title":"ICML"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10195"},{"key":"ref11","article-title":"S2s neural net models for grapheme-to-phoneme conversion","author":"zhao","year":"2015","journal-title":"InterSpeech"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414444"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324915000315"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-17"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-233"},{"key":"ref1","author":"zhang","year":"2019","journal-title":"Learning to speak fluently in a foreign language Multilingual speech synthesis and cross-language voice cloning"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855134"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3_4"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-671"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1121\/1.429469"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362120"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053797"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.10.005"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101302"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1211"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1740"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462258"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2926754"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1778"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10115"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414292"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054484"},{"key":"ref8","article-title":"Nettalk: A parallel network that learns to read aloud","author":"rosenberg","year":"1986","journal-title":"Tech Rep"},{"key":"ref7","article-title":"The carnegie mellon pronouncing dictionary","author":"weide","year":"1998"},{"key":"ref9","article-title":"Callhome american english lexicon (pronlex)","author":"kingsbury","year":"1997","journal-title":"Linguistic Data Consortium"},{"key":"ref4","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","volume":"80","author":"skerry-ryan","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2009-592"},{"key":"ref5","article-title":"An investigation of the relation between grapheme embeddings and pronunciation for tacotron-based systems","author":"perquin","year":"2021"},{"key":"ref40","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Workshop on ASRU"}],"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\/10095773.pdf?arnumber=10095773","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T22:36:14Z","timestamp":1698100574000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095773\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095773","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}