Synthesizing variation in prosody for Text-to-Speech

Rob Clark


This talk addresses the issue of producing appropriate and engaging text-to-speech. The quality of speech produced by modern text-to-speech systems is sufficiently intelligible and naturally sounding that we are now seeing it widely used in an increasing number of real world applications. While the speech generated can sound very natural, we are still a long way from ensuring it always sounds appropriate and engaging in the context of a particular discourse or dialogue. We present recent work at Google which begins to address this issue by looking at techniques to generate variation in prosody and speaking style using latent representations and discuss the problems and challenges that we face in going further.


Cite as: Clark, R. (2018) Synthesizing variation in prosody for Text-to-Speech. Proc. IberSPEECH 2018.


@inproceedings{Clark2018,
  author={Rob Clark},
  title={{Synthesizing variation in prosody for Text-to-Speech}},
  year=2018,
  booktitle={Proc. IberSPEECH 2018}
}