Sparse Autoencoders for Interpretable Emotion Control in Text-to-Speech 事件

Sparse Autoencoders for Interpretable Emotion Control in Text-to-Speech arXiv:2606.01479v1 Announce Type: new Abstract: Integrating large language models (LLMs) into text-to-speech (TTS) systems has improved speech expressiveness, yet interpretable emotional control remains challenging. Existing approaches primarily rely on external conditioning or global activation steering, offering limited insight into the internal representations underlying emotional control. In this work, we analyze emotio