Laughter Synthesis: Combining Seq2seq modeling with Transfer Learning
Audio and Speech Processing
2020-08-24 v1 Computation and Language
Machine Learning
Sound
Abstract
Despite the growing interest for expressive speech synthesis, synthesis of nonverbal expressions is an under-explored area. In this paper we propose an audio laughter synthesis system based on a sequence-to-sequence TTS synthesis system. We leverage transfer learning by training a deep learning model to learn to generate both speech and laughs from annotations. We evaluate our model with a listening test, comparing its performance to an HMM-based laughter synthesis one and assess that it reaches higher perceived naturalness. Our solution is a first step towards a TTS system that would be able to synthesize speech with a control on amusement level with laughter integration.
Cite
@article{arxiv.2008.09483,
title = {Laughter Synthesis: Combining Seq2seq modeling with Transfer Learning},
author = {Noé Tits and Kevin El Haddad and Thierry Dutoit},
journal= {arXiv preprint arXiv:2008.09483},
year = {2020}
}