超越全局情感：基于动态词级调制的细粒度情感语音合成
Beyond Global Emotion: Fine-Grained Emotional Speech Synthesis with Dynamic Word-Level Modulation
AI总结：
针对现有情感语音合成仅支持句子级全局情感、无法捕捉句内动态变化的问题，本文提出Emo-FiLM框架，利用词级情感标注与特征级线性调制实现细粒度情感控制，并构建FEDD数据集验证其有效性。
摘要：
情感文本到语音合成（E-TTS）对于创造自然且可信的人机交互至关重要。现有系统通常依赖于通过预定义标签、参考音频或自然语言提示进行的句子级控制。虽然这些方法在全局情感表达上有效，但它们无法捕捉句子内部的情感动态变化。为解决这一局限，我们提出了Emo-FiLM，一种面向基于大语言模型（LLM）的语音合成的细粒度情感建模框架。Emo-FiLM将来自emotion2vec的帧级特征与单词对齐，以获得词级情感标注，并通过特征级线性调制（FiLM）层进行映射，从而通过直接调制文本嵌入实现词级情感控制。为支持评估，我们构建了细粒度情感动态数据集（FEDD），其中包含详细的情感转换标注。实验表明，Emo-FiLM在全局和细粒度任务上均优于现有方法，证明了其在表现性语音合成中的有效性和泛化能力。
英文摘要：
Emotional text-to-speech (E-TTS) is central to creating natural and trustworthy human-computer interaction. Existing systems typically rely on sentence-level control through predefined labels, reference audio, or natural language prompts. While effective for global emotion expression, these approaches fail to capture dynamic shifts within a sentence. To address this limitation, we introduce Emo-FiLM, a fine-grained emotion modeling framework for LLM-based TTS. Emo-FiLM aligns frame-level features from emotion2vec to words to obtain word-level emotion annotations, and maps them through a Feature-wise Linear Modulation (FiLM) layer, enabling word-level emotion control by directly modulating text embeddings. To support evaluation, we construct the Fine-grained Emotion Dynamics Dataset (FEDD) with detailed annotations of emotional transitions. Experiments show that Emo-FiLM outperforms existing approaches on both global and fine-grained tasks, demonstrating its effectiveness and generality for expressive speech synthesis.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
