{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T14:32:44Z","timestamp":1767969164416,"version":"3.49.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746179","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6797-6801","source":"Crossref","is-referenced-by-count":14,"title":["Cross-Speaker Style Transfer for Text-to-Speech Using Data Augmentation"],"prefix":"10.1109","author":[{"given":"Manuel","family":"Sam Ribeiro","sequence":"first","affiliation":[{"name":"Amazon Alexa,TTS Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julian","family":"Roth","sequence":"additional","affiliation":[{"name":"Amazon Alexa,TTS Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giulia","family":"Comini","sequence":"additional","affiliation":[{"name":"Amazon Alexa,TTS Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Goeric","family":"Huybrechts","sequence":"additional","affiliation":[{"name":"Amazon Alexa,TTS Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adam","family":"Gabrys","sequence":"additional","affiliation":[{"name":"Amazon Alexa,TTS Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaime","family":"Lorenzo-Trueba","sequence":"additional","affiliation":[{"name":"Amazon Alexa,TTS Research"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref30","article-title":"Method for the subjective assessment of intermediate quality level of audio systems","author":"series","year":"2014","journal-title":"International Telecommunication Union (ITU) Radiocommunication Assembly"},{"key":"ref10","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2014","journal-title":"International Conference on Learning Representations"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1854"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2985"},{"key":"ref14","article-title":"Multi-reference Tacotron by intercross training for style disentangling, transfer and control in speech synthesis","author":"bian","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.03.005"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1407"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616249"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3021758"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003859"},{"key":"ref28","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"ICLRE"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1424"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-314"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1446"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414444"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-838"},{"key":"ref8","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with Tacotron","author":"skerry-ryan","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054556"},{"key":"ref2","article-title":"A survey on neural speech synthesis","author":"tan","year":"2021"},{"key":"ref9","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-979"},{"key":"ref22","article-title":"Non-autoregressive tts with explicit duration modelling for low-resource highly expressive speech","author":"shah","year":"2021","journal-title":"Workshop on Speech Synthesis"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413466"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1251"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414408"},{"key":"ref26","first-page":"5210","article-title":"Autovc: Zero-shot voice style transfer with only autoencoder loss","author":"qian","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054734"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746179.pdf?arnumber=9746179","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:10:01Z","timestamp":1660594201000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746179\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746179","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}