Multi-Modal Automatic Prosody Annotation with Contrastive Pretraining of SSWP
Abstract
In expressive and controllable Text-to-Speech (TTS), explicit prosodic features significantly improve the naturalness and controllability of synthesised speech. However, manual prosody annotation is labor-intensive and inconsistent. To address this issue, a two-stage automatic annotation pipeline is novelly proposed in this paper. In the first stage, we use contrastive pretraining of Speech-Silence and Word-Punctuation (SSWP) pairs to enhance prosodic information in latent representations. In the second stage, we build a multi-modal prosody annotator, comprising pretrained encoders, a text-speech fusing scheme, and a sequence classifier. Experiments on English prosodic boundaries demonstrate that our method achieves state-of-the-art (SOTA) performance with 0.72 and 0.93 f1 score for Prosodic Word and Prosodic Phrase boundary respectively, while bearing remarkable robustness to data scarcity.
Cite
@article{arxiv.2309.05423,
title = {Multi-Modal Automatic Prosody Annotation with Contrastive Pretraining of SSWP},
author = {Jinzuomu Zhong and Yang Li and Hui Huang and Korin Richmond and Jie Liu and Zhiba Su and Jing Guo and Benlai Tang and Fengjie Zhu},
journal= {arXiv preprint arXiv:2309.05423},
year = {2024}
}