{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:05:47Z","timestamp":1730297147120,"version":"3.28.0"},"reference-count":30,"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\/slt54892.2023.10022506","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T13:54:03Z","timestamp":1674827643000},"page":"984-990","source":"Crossref","is-referenced-by-count":2,"title":["Remap, Warp and Attend: Non-Parallel Many-to-Many Accent Conversion with Normalizing Flows"],"prefix":"10.1109","author":[{"given":"Abdelhamid","family":"Ezzerg","sequence":"first","affiliation":[{"name":"Amazon Alexa"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Merritt","sequence":"additional","affiliation":[{"name":"Amazon Alexa"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kayoko","family":"Yanagisawa","sequence":"additional","affiliation":[{"name":"Amazon Alexa"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Piotr","family":"Bilinski","sequence":"additional","affiliation":[{"name":"Amazon Alexa"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Magdalena","family":"Proszewska","sequence":"additional","affiliation":[{"name":"Amazon Alexa"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kamil","family":"Pokora","sequence":"additional","affiliation":[{"name":"Amazon Alexa"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Renard","family":"Korzeniowski","sequence":"additional","affiliation":[{"name":"Amazon Alexa"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roberto","family":"Barra-Chicote","sequence":"additional","affiliation":[{"name":"Amazon Alexa"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Korzekwa","sequence":"additional","affiliation":[{"name":"Amazon Alexa"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"3385","article-title":"Articulatory-based conversion of foreign accents with deep neural networks","author":"aryal","year":"2015","journal-title":"InterSpeech"},{"key":"ref12","article-title":"Improving accent conversion with reference encoder and end-to-end text-to-speech","volume":"abs 2005 9271","author":"li","year":"2020","journal-title":"ArXiv"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3060813"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855097"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414444"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462258"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1778"},{"key":"ref2","article-title":"CopyCat: Many-to-Many Fine-Grained Prosody Transfer for Neural Text-to-Speech","author":"karlapati","year":"2020","journal-title":"InterSpeech"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.01.008"},{"key":"ref17","first-page":"1","article-title":"Normalizing Flows: An Introduction and Review of Current Methods","author":"kobyzev","year":"2020","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"journal-title":"Accent and speaker disentanglement in many-to-many voice conversion","year":"2020","author":"wang","key":"ref16"},{"key":"ref19","article-title":"Glow: Generative Flow with Invertible 1×1 Convolutions","volume":"31","author":"kingma","year":"2018","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref18","first-page":"2722","article-title":"Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design","author":"ho","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning"},{"key":"ref24","article-title":"Blow: a single-scale hyperconditioned flow for non-parallel raw-audio voice conversion","author":"serr\u00e1","year":"2019","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref23","article-title":"Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis","author":"valle","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746368"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2892235"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054484"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1774"},{"key":"ref21","first-page":"8067","article-title":"Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search","volume":"33","author":"kim","year":"2020","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref27","article-title":"Montreal forced aligner: Trainable text-speech alignment using kaldi","author":"mcauliffe","year":"2017","journal-title":"Proceedings of the 18th Conference of the International Speech Communication Association"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413466"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855134"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-28"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-671"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1789"},{"key":"ref3","first-page":"5210","article-title":"AutoVC: Zero-shot voice style transfer with only autoencoder loss","author":"qian","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.10.005"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(01)00009-7"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2023,1,9]]},"location":"Doha, Qatar","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\/10022506.pdf?arnumber=10022506","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T17:08:09Z","timestamp":1676912889000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022506\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10022506","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}