DUET: Unified Dual-Space Emotion Control for Diffusion and Flow-Matching Driven Text-to-Speech

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhang, Xu, Cao, Longbing, Wu, Zhangkai
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914619282423808
author Zhang, Xu
Cao, Longbing
Wu, Zhangkai
author_facet Zhang, Xu
Cao, Longbing
Wu, Zhangkai
contents Diffusion and flow-matching based text-to-speech (TTS) models excel in naturalness but often lack explicit emotion control, as emotional signals remain entangled with speaker identity. We discover that emotion embedding emerges as a linearly decodable direction of frozen hidden states, nearly orthogonal to the direction embedding speaker identity. This inspires a plug-and-play framework DUET for emotion control over pretrained diffusion and flow-matching based TTS models. During generation, DUET unifies dual-space control to achieve fine-grained emotion intervention in a single per-step update: hidden space steering shifts generation along the target emotion direction, while mel-space guidance refines spectral details through gradients backpropagated from a differentiable vocoder. We validate DUET on five architecturally diverse pretrained TTS backbones across three datasets, where it outperforms 10 supervised state-of-the-art emotional TTS baselines across paradigms and achieves the highest human-rated emotion appropriateness. To further showcase its qualitative behavior, we deploy DUET on an Ameca humanoid robot, where it produces richly expressive emotional speech on the humanoid, demonstrating the strong potential for plug-and-play affective interaction for embodied agents.
format Preprint
id arxiv_https___arxiv_org_abs_2606_00066
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DUET: Unified Dual-Space Emotion Control for Diffusion and Flow-Matching Driven Text-to-Speech
Zhang, Xu
Cao, Longbing
Wu, Zhangkai
Sound
Audio and Speech Processing
Diffusion and flow-matching based text-to-speech (TTS) models excel in naturalness but often lack explicit emotion control, as emotional signals remain entangled with speaker identity. We discover that emotion embedding emerges as a linearly decodable direction of frozen hidden states, nearly orthogonal to the direction embedding speaker identity. This inspires a plug-and-play framework DUET for emotion control over pretrained diffusion and flow-matching based TTS models. During generation, DUET unifies dual-space control to achieve fine-grained emotion intervention in a single per-step update: hidden space steering shifts generation along the target emotion direction, while mel-space guidance refines spectral details through gradients backpropagated from a differentiable vocoder. We validate DUET on five architecturally diverse pretrained TTS backbones across three datasets, where it outperforms 10 supervised state-of-the-art emotional TTS baselines across paradigms and achieves the highest human-rated emotion appropriateness. To further showcase its qualitative behavior, we deploy DUET on an Ameca humanoid robot, where it produces richly expressive emotional speech on the humanoid, demonstrating the strong potential for plug-and-play affective interaction for embodied agents.
title DUET: Unified Dual-Space Emotion Control for Diffusion and Flow-Matching Driven Text-to-Speech
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2606.00066