ComedicSpeech: Text To Speech For Stand-up Comedies in Low-Resource Scenarios
Abstract
Text to Speech (TTS) models can generate natural and high-quality speech, but it is not expressive enough when synthesizing speech with dramatic expressiveness, such as stand-up comedies. Considering comedians have diverse personal speech styles, including personal prosody, rhythm, and fillers, it requires real-world datasets and strong speech style modeling capabilities, which brings challenges. In this paper, we construct a new dataset and develop ComedicSpeech, a TTS system tailored for the stand-up comedy synthesis in low-resource scenarios. First, we extract prosody representation by the prosody encoder and condition it to the TTS model in a flexible way. Second, we enhance the personal rhythm modeling by a conditional duration predictor. Third, we model the personal fillers by introducing comedian-related special tokens. Experiments show that ComedicSpeech achieves better expressiveness than baselines with only ten-minute training data for each comedian. The audio samples are available at https://xh621.github.io/stand-up-comedy-demo/
Keywords
Cite
@article{arxiv.2305.12200,
title = {ComedicSpeech: Text To Speech For Stand-up Comedies in Low-Resource Scenarios},
author = {Yuyue Wang and Huan Xiao and Yihan Wu and Ruihua Song},
journal= {arXiv preprint arXiv:2305.12200},
year = {2023}
}
Comments
5 pages, 4 tables, 2 figure