作者位次 #5/7ACL 2026Poster· Natural Language Processing
Rectifying the Emotional Flow: Aligning Priors and Dynamic Guidance for High-Arousal Text-to-Speech
Fangming Feng · Dongjie Fu · Zequn Xie · Yu Zhang · Yangyang Wu · Zhou Zhao · Tao Jin
摘要
While diffusion and flow-matching models have advanced TTS, generating high-arousal emotions remains a persistent challenge due to the trade-off between stability and expressiveness. Existing systems often suffer from linguistic collapse when pursuing high intensity or fail to meet target emotion...