EmoTra-TTS：用于语音合成的流畅句内情感转换
EmoTra-TTS: Smooth Intra-Utterance Emotion Transitions for Speech Synthesis
- LIGHTSPEED
- National University of Singapore（新加坡国立大学）
- Nanyang Technological University（南洋理工大学）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
EmoTra-TTS针对现有情感TTS系统与情感时间特性不匹配的问题，采用多遍流混合管道、双阶段VAD条件及方向-幅度解耦注入，实现流畅句内情感转换，且性能优于SOTA基线与商业系统。
中文摘要 AI 辅助
情感动力学的心理学研究表明，人类情感是一个连续演变的过程：情绪在数秒内上升、衰减并发生转换。然而，当前的情感文本语音合成（TTS）系统，每句仅以单一离散标签或静态嵌入作为条件，与情感的时间特性根本不匹配。尽管近期基于大语言模型（LLM）的TTS系统可能通过文本理解隐式改变韵律，但这种改变既无法明确控制，也不足以实现精准的句内目标转换。我们解决了三项挑战：（1）多遍流混合管道合成与帧对齐的转换音频，规避了自然句内转换数据稀缺的问题；（2）双阶段效价-唤醒度-支配度（VAD）条件通过帧级VAD嵌入，指导LLM中的韵律规划和流解码器中的声学实现；（3）方向-幅度解耦注入在结构上分离情感方向与注入幅度，防止内容退化。EmoTra-TTS仅增加0.43%的参数，无延迟开销，在情感转换质量上实现30%-87%的相对提升，经成对偏好测试验证，与四个SOTA基线和两个商业系统相比，整体胜率达64.4%-79.5%。
英文摘要
Psychological research on emotion dynamics has established that human affect is a continuous, evolving process: emotions rise, decay, and transition within seconds. Current emotional text-to-speech (TTS) systems, however, condition on a single discrete label or static embedding per utterance, fundamentally misaligning with the temporal nature of affect. While recent LLM-based TTS systems may implicitly vary prosody through text understanding, such variation is neither explicitly controllable nor precise enough for targeted intra-utterance transitions. We address three challenges: (1) a multi-pass flow blending pipeline synthesizes frame-aligned transition audio, circumventing the scarcity of natural intra-utterance transitions; (2) dual-stage Valence-Arousal-Dominance (VAD) conditioning guides prosodic planning in the LLM and acoustic realization in the flow decoder via frame-level VAD embeddings; (3) direction-magnitude decoupled injection structurally separates emotion direction from injection magnitude, preventing content degradation. EmoTra-TTS adds only +0.43% parameters with no latency overhead, achieves 30%-87% relative improvement on emotion transition quality, corroborated by 64.4%-79.5% overall win rates in pairwise preference tests against four SOTA baselines and two commercial systems.
