Spotlight-TTS: Spotlighting the Style via Voiced-Aware Style Extraction and Style Direction Adjustment for Expressive Text-to-Speech
This work addresses the problem of improving expressiveness and quality in text-to-speech synthesis, which is incremental as it builds on existing style embedding methods.
The paper tackles the challenge of synthesizing high-quality expressive speech in text-to-speech by proposing Spotlight-TTS, which uses voiced-aware style extraction and style direction adjustment to enhance expressiveness and speech quality, achieving superior performance over baseline models in experiments.
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 Spotlight-TTS, 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. Our audio samples are publicly available.