Enregistré dans:
Détails bibliographiques
Auteurs principaux: Peng, Yizhou, Ma, Yukun, Zhang, Chong, Chao, Yi-Wen, Ni, Chongjia, Ma, Bin, Chng, Eng Siong
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2510.13293
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913145539264512
author Peng, Yizhou
Ma, Yukun
Zhang, Chong
Chao, Yi-Wen
Ni, Chongjia
Ma, Bin
Chng, Eng Siong
author_facet Peng, Yizhou
Ma, Yukun
Zhang, Chong
Chao, Yi-Wen
Ni, Chongjia
Ma, Bin
Chng, Eng Siong
contents While Text-to-Speech (TTS) systems enable emotional control via natural-language instructions, expressiveness, naturalness, and speech quality degrade when the target emotion conflicts with the textual semantics. We propose a Cross-modal Consistency Guided Classifier-Free Guidance (CCG-CFG) method with dynamic scales based on the degree of inconsistency between the text emotion and the explicit speech emotion, replacing the dropout condition with the text emotion. We also distill the CCG-CFG guidance signal using a hard-sample mining strategy, improving the TTS model's emotional alignment capability. Evaluations on five emotional corpora and two TTS benchmarks show that our approaches applied to CosyVoice2 achieve up to a 12% absolute improvement in emotion-recognition accuracy and a 10% relative improvement in subjective scores, outperforming baselines including HierSpeech++, Qwen3-TTS, and original CosyVoice2, while preserving intelligibility, naturalness, and high speech quality.
format Preprint
id arxiv_https___arxiv_org_abs_2510_13293
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Cross-modal Consistency Guidance for Robust Emotion Control in Auto-Regressive TTS Models
Peng, Yizhou
Ma, Yukun
Zhang, Chong
Chao, Yi-Wen
Ni, Chongjia
Ma, Bin
Chng, Eng Siong
Computation and Language
While Text-to-Speech (TTS) systems enable emotional control via natural-language instructions, expressiveness, naturalness, and speech quality degrade when the target emotion conflicts with the textual semantics. We propose a Cross-modal Consistency Guided Classifier-Free Guidance (CCG-CFG) method with dynamic scales based on the degree of inconsistency between the text emotion and the explicit speech emotion, replacing the dropout condition with the text emotion. We also distill the CCG-CFG guidance signal using a hard-sample mining strategy, improving the TTS model's emotional alignment capability. Evaluations on five emotional corpora and two TTS benchmarks show that our approaches applied to CosyVoice2 achieve up to a 12% absolute improvement in emotion-recognition accuracy and a 10% relative improvement in subjective scores, outperforming baselines including HierSpeech++, Qwen3-TTS, and original CosyVoice2, while preserving intelligibility, naturalness, and high speech quality.
title Cross-modal Consistency Guidance for Robust Emotion Control in Auto-Regressive TTS Models
topic Computation and Language
url https://arxiv.org/abs/2510.13293