Audio samples - ZCL-EDiff

Anonymous demo page for paper ZCL-EDiff

  • VALL-E-X: https://github.com/Plachtaa/VALL-E-X
  • YourTTS: https://github.com/coqui-ai/TTS
  • X-E-Speech: https://github.com/ X-E-Speech/X-E-Speech-code

    • Seen:

    Cross-lingual emotional Text-to-speech(English Text):

    Text Reference speech X-E-Speech VALL-E-X YourTTS ZCL-EDiff(proposed)
    Because he was a man with infinite resource and sagacity.
    Because he was a man with infinite resource and sagacity.
    This was the twenty fifth of november, seventeen eighty three.
    This was the twenty fifth of november, seventeen eighty three.
    Why should i care though David's lips were twitching?
    Why should i care though David's lips were twitching?
    In which fox loses a tail and its elder sister finds one.
    In which fox loses a tail and its elder sister finds one.
    All smile were real and the happier，the more sincere .
    All smile were real and the happier，the more sincere .

    Cross-lingual emotional Text-to-speech(Chinese Text):

    Text Reference speech VALL-E-X YourTTS ZCL-EDiff(proposed)
    就是这个意思，你又聪明又好看。
    就经常去我们宿舍附近的酒吧。
    我最好的朋友就约会过。

    Unseen:

    Intra-lingual emotional Text-to-speech(English Text):

    Text Reference speech X-E-Speech VALL-E-X YourTTS ZCL-EDiff(proposed)
    Because he was a man with infinite resource and sagacity.
    If you love golf, then you can publish things about golf.
    All smile were real and the happier，the more sincere .

    Cross-lingual emotional Text-to-speech(Chinses Text):

    Text Reference speech VALL-E-X YourTTS ZCL-EDiff(proposed)
    就经常去我们宿舍附近的酒吧。
    就是这个意思，你又聪明又好看。
    白羊座的主持人有什么