Multi-Modal Automatic Prosody Annotation with Contrastive Pretraining of SSWP

• Published in: arXiv.org 2024-06
• Main Authors: Zhong, Jinzuomu, Yang, Li, Huang, Hui, Richmond, Korin, Liu, Jie, Su, Zhiba, Guo, Jing, Tang, Benlai, Zhu, Fengjie
• Format: Article
• Language: English
• Subjects: Annotations; Coders; Hammers; Linguistics; Speech; Speech recognition
• ISSN: 2331-8422

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.