Total-Duration-Aware Duration Modeling for Text-to-Speech Systems
Abstract
Accurate control of the total duration of generated speech by adjusting the speech rate is crucial for various text-to-speech (TTS) applications. However, the impact of adjusting the speech rate on speech quality, such as intelligibility and speaker characteristics, has been underexplored. In this work, we propose a novel total-duration-aware (TDA) duration model for TTS, where phoneme durations are predicted not only from the text input but also from an additional input of the total target duration. We also propose a MaskGIT-based duration model that enhances the diversity and quality of the predicted phoneme durations. Our results demonstrate that the proposed TDA duration models achieve better intelligibility and speaker similarity for various speech rate configurations compared to the baseline models. We also show that the proposed MaskGIT-based model can generate phoneme durations with higher quality and diversity compared to its regression or flow-matching counterparts.
Keywords
Cite
@article{arxiv.2406.04281,
title = {Total-Duration-Aware Duration Modeling for Text-to-Speech Systems},
author = {Sefik Emre Eskimez and Xiaofei Wang and Manthan Thakker and Chung-Hsien Tsai and Canrun Li and Zhen Xiao and Hemin Yang and Zirun Zhu and Min Tang and Jinyu Li and Sheng Zhao and Naoyuki Kanda},
journal= {arXiv preprint arXiv:2406.04281},
year = {2024}
}
Comments
Accepted to Interspeech 2024