{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T21:50:46Z","timestamp":1766267446841},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8682589","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"6800-6804","source":"Crossref","is-referenced-by-count":14,"title":["Attention-based Wavenet Autoencoder for Universal Voice Conversion"],"prefix":"10.1109","author":[{"given":"Adam","family":"Polyak","sequence":"first","affiliation":[]},{"given":"Lior","family":"Wolf","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"year":"2018","key":"ref31","article-title":"en-US-Wavenet-E"},{"article-title":"Tacotron 2 – pytorch implementation with faster-than-realtime inference","year":"2018","author":"puri","key":"ref30"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953215"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-116"},{"key":"ref12","article-title":"Auto-Encoding Variational Bayes","author":"kingma","year":"2014","journal-title":"ICLRE"},{"key":"ref13","article-title":"Voice Conversion from Nonparallel Corpora Using Variational Auto-Encoder","author":"hsu","year":"2016","journal-title":"APSIPA"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-63"},{"key":"ref15","article-title":"Wasserstein Generative Adversarial Networks","author":"arjovsky","year":"2017","journal-title":"ICML"},{"key":"ref16","article-title":"Deep voice: Real-time neural text-to-speech","author":"arik","year":"2017","journal-title":"ICML"},{"key":"ref17","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","author":"arik","year":"2017","journal-title":"NIPS"},{"key":"ref18","article-title":"Deep voice 3: 2000-speaker neural text-to-speech","author":"ping","year":"2018","journal-title":"ICLRE"},{"key":"ref19","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","author":"van den oord","year":"2018","journal-title":"ICML"},{"key":"ref28","article-title":"The Blizzard challenge 2011","author":"king","year":"2011","journal-title":"Blizzard Challenge Workshop"},{"article-title":"Generating sequences with recurrent neural networks","year":"2013","author":"graves","key":"ref4"},{"article-title":"The LJ speech dataset","year":"2017","author":"ito","key":"ref27"},{"article-title":"A universal music translation network","year":"2018","author":"mor","key":"ref3"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.21437\/Odyssey.2018-28","article-title":"The voice conversion challenge 2018: Promoting development of parallel and nonparallel methods","author":"lorenzo-trueba","year":"2018"},{"key":"ref29","article-title":"The Blizzard challenge 2013","author":"king","year":"2013","journal-title":"Blizzard Challenge Workshop"},{"key":"ref5","article-title":"Attention is All you Need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2038669"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1190"},{"key":"ref2","article-title":"Neural audio synthesis of musical notes with wavenet autoencoders","author":"engel","year":"2017","journal-title":"ICML"},{"key":"ref9","article-title":"Text-independent voice conversion using speaker model alignment method from non-parallel speech","author":"song","year":"2014","journal-title":"INTER-SPEECH"},{"article-title":"Wavenet: A generative model for raw audio","year":"2016","author":"van den oord","key":"ref1"},{"key":"ref20","article-title":"Char2wav: End-to-end speech synthesis","author":"sotelo","year":"2017","journal-title":"ICLR Workshop"},{"key":"ref22","article-title":"Natural TTS synthesis by conditioning wavenet on mel spectrogram predictions","author":"shen","year":"2017","journal-title":"ICASSP"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: A fully end-to-end text-to-speech synthesis model","author":"wang","year":"2017","journal-title":"InterSpeech"},{"key":"ref24","article-title":"Fitting new speakers based on a short un-transcribed sample","author":"nachmani","year":"2018","journal-title":"ICML"},{"key":"ref23","article-title":"VoiceLoop: Voice Fitting and Synthesis via a Phonological Loop","author":"taigman","year":"2018","journal-title":"ICLRE"},{"key":"ref26","article-title":"Fast and accurate deep network learning by exponential linear units (elus)","author":"clevert","year":"2017","journal-title":"ICLRE"},{"key":"ref25","article-title":"Domain-adversarial training of neural networks","author":"ganin","year":"2016","journal-title":"J Mach Learn Res"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, United Kingdom","end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08682589.pdf?arnumber=8682589","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,14]],"date-time":"2022-07-14T23:14:19Z","timestamp":1657840459000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8682589\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8682589","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}