eduzhai > Applied Sciences > Engineering >

Laughter Synthesis Combining Seq2seq modeling with Transfer Learning

  • king
  • (0) Download
  • 20210507
  • Save

... pages left unread,continue reading

Document pages: 5 pages

Abstract: Despite the growing interest for expressive speech synthesis, synthesis ofnonverbal expressions is an under-explored area. In this paper we propose anaudio laughter synthesis system based on a sequence-to-sequence TTS synthesissystem. We leverage transfer learning by training a deep learning model tolearn to generate both speech and laughs from annotations. We evaluate ourmodel with a listening test, comparing its performance to an HMM-based laughtersynthesis one and assess that it reaches higher perceived naturalness. Oursolution is a first step towards a TTS system that would be able to synthesizespeech with a control on amusement level with laughter integration.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...