Voiced-Aware Style Extraction and Style Direction Adjustment for Expressive Text-to-Speech

TL;DR

SpotlightTTS introduces a voiced-aware style extraction and style direction adjustment method to enhance expressive speech synthesis, focusing on voiced regions and optimizing style integration for improved quality and style transfer.

Contribution

The paper presents a novel voiced-aware style extraction and style direction adjustment technique for expressive TTS, improving style transfer and speech quality.

Findings

Outperforms baseline models in expressiveness and quality

Enhances style transfer capability in TTS

Maintains continuity across speech regions

Abstract

Recent advances in expressive text-to-speech (TTS) have introduced diverse methods based on style embedding extracted from reference speech. However, synthesizing high-quality expressive speech remains challenging. We propose SpotlightTTS, which exclusively emphasizes style via voiced-aware style extraction and style direction adjustment. Voiced-aware style extraction focuses on voiced regions highly related to style while maintaining continuity across different speech regions to improve expressiveness. We adjust the direction of the extracted style for optimal integration into the TTS model, which improves speech quality. Experimental results demonstrate that Spotlight-TTS achieves superior performance compared to baseline models in terms of expressiveness, overall speech quality, and style transfer capability.