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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Kim, Nam-Gyu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911275176427520
author Kim, Nam-Gyu
author_facet Kim, Nam-Gyu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_14824
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Voiced-Aware Style Extraction and Style Direction Adjustment for Expressive Text-to-Speech
Kim, Nam-Gyu
Sound
Artificial Intelligence
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.
title Voiced-Aware Style Extraction and Style Direction Adjustment for Expressive Text-to-Speech
topic Sound
Artificial Intelligence
url https://arxiv.org/abs/2511.14824