GlobalRhythmStyleTransferWithoutTextTranscriptionsKaizhiQian12YangZhang12ShiyuChang12JinjunXiong2ChuangGan12DavidCox12MarkHasegawa-Johnson3Abstractwhichthespeakerexpressesthecontent.Therearetwomajo...
EncodingMusicalStylewithTransformerAutoencodersKristyChoi1CurtisHawthorne2IanSimon2MonicaDinculescu2JesseEngel2Abstracttwofold.First,Transformers(Vaswanietal.,2017)andtheirvariantsexcelasunconditio...
AUTOVC:Zero-ShotVoiceStyleTransferwithOnlyAutoencoderLossKaizhiQian1YangZhang23ShiyuChang23XuesongYang1MarkHasegawa-Johnson1Abstractingdata,i.e.speechpairswherethetwospeakersutterthesamesentences.O...
StyleTokens:UnsupervisedStyleModeling,ControlandTransferinEnd-to-EndSpeechSynthesisYuxuanWang1DaisyStanton1YuZhang1RJSkerry-Ryan1EricBattenberg1JoelShor1YingXiao1FeiRen1YeJia1RifA.Saurous1Abstracto...