New TTS method boosts emotion control accuracy by 12%

Researchers have developed a new method called Cross-modal Consistency Guided Classifier-Free Guidance (CCG-CFG) to improve emotion control in auto-regressive Text-to-Speech (TTS) models. This technique dynamically adjusts guidance scales based on the conflict between textual and desired speech emotions, enhancing emotional alignment. When applied to the CosyVoice2 model, this approach led to significant improvements in emotion recognition accuracy and subjective quality scores, outperforming existing methods like HierSpeech++ and Qwen3-TTS. AI

影响 Enhances TTS expressiveness and accuracy, potentially leading to more natural and emotionally resonant AI-generated speech.

排序理由 The cluster contains a research paper detailing a new method for TTS emotion control. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

• CosyVoice2
• Cross-modal Consistency Guided Classifier-Free Guidance
• HierSpeech++
• Qwen3-TTS
• Yizhou Peng

• 论文
• 模型发布

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →