Meta-StyleSpeech:Multi-SpeakerAdaptiveText-to-SpeechGenerationDongchanMin1DongBokLee1EunhoYang12SungJuHwang12Abstractsynthesis.ThemajorityoftheTTSmodelsaimtosynthe-sizehighqualityspeechofasinglespe...
Grad-TTS:ADiffusionProbabilisticModelforText-to-SpeechVadimPopov1IvanVovk12VladimirGogoryan12TasnimaSadekova1MikhailKudinov1Abstract2014)andNormalizingFlows(Rezende&Mohamed,2015)wereusedinthedesign...
EfficientTTS:AnEfficientandHigh-QualityText-to-SpeechArchitectureChenfengMiao1ShuangLiang1ZhengchenLiu1MinchuanChen1JunMa1ShaojunWang1JingXiao1Abstractsivemodelshasbeensubstantiallypromoted,thesynt...
Non-AutoregressiveNeuralText-to-SpeechKainanPeng∗1WeiPing∗1ZhaoSong∗1KexinZhao∗1Abstractgram.Thispipelinerequiresmuchlessexpertknowledgeandonlyneedspairsofaudioandtranscriptastrainingdata.Inthi...
DeepVoice:Real-timeNeuralText-to-SpeechSercanO¨.Arık1MikeChrzanowski1AdamCoates1GregoryDiamos1AndrewGibiansky1YongguoKang2XianLi2JohnMiller1AndrewNg1JonathanRaiman1ShubhoSengupta1MohammadShoeybi1...