{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T16:16:40Z","timestamp":1778602600743,"version":"3.51.4"},"reference-count":33,"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\/icassp43922.2022.9747239","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"7902-7906","source":"Crossref","is-referenced-by-count":14,"title":["Voice Filter: Few-Shot Text-to-Speech Speaker Adaptation Using Voice Conversion as a Post-Processing Module"],"prefix":"10.1109","author":[{"given":"Adam","family":"Gabrys","sequence":"first","affiliation":[{"name":"Alexa AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Goeric","family":"Huybrechts","sequence":"additional","affiliation":[{"name":"Alexa AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manuel Sam","family":"Ribeiro","sequence":"additional","affiliation":[{"name":"Alexa AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chung-Ming","family":"Chien","sequence":"additional","affiliation":[{"name":"National Taiwan University (NTU)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julian","family":"Roth","sequence":"additional","affiliation":[{"name":"Alexa AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giulia","family":"Comini","sequence":"additional","affiliation":[{"name":"Alexa AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roberto","family":"Barra-Chicote","sequence":"additional","affiliation":[{"name":"Alexa AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bartek","family":"Perz","sequence":"additional","affiliation":[{"name":"Alexa AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaime","family":"Lorenzo-Trueba","sequence":"additional","affiliation":[{"name":"Alexa AI"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1251"},{"key":"ref32","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":"Advances in neural information processing systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref30","article-title":"High fidelity speech synthesis with adversarial networks","author":"bi?kowski","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref10","article-title":"Neural discrete representation learning","volume":"30","author":"van den oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref11","first-page":"14866","article-title":"Generating diverse high-fidelity images with vq-vae-2","author":"razavi","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1443"},{"key":"ref13","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2096"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1737"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1032"},{"key":"ref17","article-title":"Neural voice cloning with a few samples","volume":"31","author":"arik","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref18","first-page":"4485","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"2018","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1705"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1403"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404842"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2730"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413466"},{"key":"ref29","first-page":"518","article-title":"A robust algorithm for pitch tracking (RAPT)","volume":"495","author":"talkin","year":"1995","journal-title":"Speech Coding and Synthesis"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403331"},{"key":"ref8","article-title":"Voiceloop: Voice fitting and synthesis via a phonological loop","author":"taigman","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683862"},{"key":"ref9","article-title":"Sample efficient adaptive text-to-speech","author":"chen","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682168"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054301"},{"key":"ref22","article-title":"Adaspeech: Adaptive text to speech for custom voice","author":"chen","year":"2021","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref21","article-title":"Adadurian: Few-shot adaptation for neural text-to-speech with durian","author":"zhang","year":"2020"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"96","DOI":"10.21437\/SSW.2021-17","article-title":"Non-Autoregressive TTS with Explicit Duration Modelling for Low-Resource Highly Expressive Speech","author":"shah","year":"2021","journal-title":"Proc 11th ISCA Speech Synthesis Workshop (SSW 11)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616305"},{"key":"ref26","first-page":"3918","article-title":"Parallel wavenet: Fast high-fidelity speech synthesis","author":"oord","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1745"}],"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\/09747239.pdf?arnumber=9747239","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T16:11:52Z","timestamp":1660579912000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747239\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747239","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}