EME-TTS: Unlocking the Emphasis and Emotion Link in Speech Synthesis

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Haoxun, Qu, Leyuan, Hu, Jiaxi, Li, Taihao
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918094613512192
author Li, Haoxun
Qu, Leyuan
Hu, Jiaxi
Li, Taihao
author_facet Li, Haoxun
Qu, Leyuan
Hu, Jiaxi
Li, Taihao
contents In recent years, emotional Text-to-Speech (TTS) synthesis and emphasis-controllable speech synthesis have advanced significantly. However, their interaction remains underexplored. We propose Emphasis Meets Emotion TTS (EME-TTS), a novel framework designed to address two key research questions: (1) how to effectively utilize emphasis to enhance the expressiveness of emotional speech, and (2) how to maintain the perceptual clarity and stability of target emphasis across different emotions. EME-TTS employs weakly supervised learning with emphasis pseudo-labels and variance-based emphasis features. Additionally, the proposed Emphasis Perception Enhancement (EPE) block enhances the interaction between emotional signals and emphasis positions. Experimental results show that EME-TTS, when combined with large language models for emphasis position prediction, enables more natural emotional speech synthesis while preserving stable and distinguishable target emphasis across emotions. Synthesized samples are available on-line.
format Preprint
id arxiv_https___arxiv_org_abs_2507_12015
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EME-TTS: Unlocking the Emphasis and Emotion Link in Speech Synthesis
Li, Haoxun
Qu, Leyuan
Hu, Jiaxi
Li, Taihao
Sound
Audio and Speech Processing
In recent years, emotional Text-to-Speech (TTS) synthesis and emphasis-controllable speech synthesis have advanced significantly. However, their interaction remains underexplored. We propose Emphasis Meets Emotion TTS (EME-TTS), a novel framework designed to address two key research questions: (1) how to effectively utilize emphasis to enhance the expressiveness of emotional speech, and (2) how to maintain the perceptual clarity and stability of target emphasis across different emotions. EME-TTS employs weakly supervised learning with emphasis pseudo-labels and variance-based emphasis features. Additionally, the proposed Emphasis Perception Enhancement (EPE) block enhances the interaction between emotional signals and emphasis positions. Experimental results show that EME-TTS, when combined with large language models for emphasis position prediction, enables more natural emotional speech synthesis while preserving stable and distinguishable target emphasis across emotions. Synthesized samples are available on-line.
title EME-TTS: Unlocking the Emphasis and Emotion Link in Speech Synthesis
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2507.12015