Abstract
Current emotional Text-To-Speech (TTS) and style transfer methods rely on reference encoders to control global style or emotion vectors, but do not capture nuanced acoustic details of the reference speech. To this end, we propose a novel emotional TTS method that enables fine-grained phoneme-level emotion embedding prediction while disentangling intrinsic attributes of the reference speech. The proposed method employs a style disentanglement method to guide two feature extractors, reducing mutual information between timbre and emotion features, and effectively separating distinct style components from the reference speech. Experimental results demonstrate that our method outperforms baseline TTS systems in generating natural and emotionally rich speech. This work highlights the potential of disentangled and fine-grained representations in advancing the quality and flexibility of emotional TTS systems.
Abstract (translated)
当前的情感文本到语音（TTS）和风格转换方法依赖于参考编码器来控制全局风格或情感向量，但无法捕捉参考语音中的细微声学细节。为此，我们提出了一种新的情感TTS方法，该方法能够在分离参考语音的内在属性的同时，在音素级别上进行精细的情感嵌入预测。所提出的方法采用了一种风格解耦方法，指导两个特征提取器减少音色和情感特征之间的相互信息，并有效地从参考语音中区分出不同的风格成分。实验结果表明，与基线TTS系统相比，我们的方法在生成自然且情感丰富的语音方面表现更佳。这项工作强调了在提高情感TTS系统的质量和灵活性方面，解耦的细粒度表示法的巨大潜力。
URL
https://arxiv.org/abs/2510.01722
