Conversational and Social Laughter Synthesis with WaveNet

Hiroki Mori, Tomohiro Nagata, Yoshiko Arimoto


The studies of laughter synthesis are relatively few, and they are still in a preliminary stage. We explored the possibility of applying WaveNet to laughter synthesis. WaveNet is potentially more suitable to model laughter waveforms that do not have a well-established theory of production like speech signals. Conversational laughter was modelled with a spontaneous dialogue speech corpus based on WaveNet. To obtain more stable laughter generation, conditioning WaveNet by power contour was proposed. Experimental results showed that the synthesized laughter by WaveNet was perceived as closer to natural laughter than HMM-based synthesized laughter.


 DOI: 10.21437/Interspeech.2019-2131

Cite as: Mori, H., Nagata, T., Arimoto, Y. (2019) Conversational and Social Laughter Synthesis with WaveNet. Proc. Interspeech 2019, 520-523, DOI: 10.21437/Interspeech.2019-2131.


@inproceedings{Mori2019,
  author={Hiroki Mori and Tomohiro Nagata and Yoshiko Arimoto},
  title={{Conversational and Social Laughter Synthesis with WaveNet}},
  year=2019,
  booktitle={Proc. Interspeech 2019},
  pages={520--523},
  doi={10.21437/Interspeech.2019-2131},
  url={http://dx.doi.org/10.21437/Interspeech.2019-2131}
}