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

ArXiv CS.CL2026-06-02NEWSen作者: Hongfei Du, Jiacheng Shi, Sidi Lu, Gang Zhou, Ye Gao

查看原文 →

Sparse Autoencoders for Interpretable Emotion Control in Text-to-Speech · 相关技术

相关技术

sparse autoencoder feature-level intervention framework sparse latent features SAE TTS LLM text-to-speech (TTS)large language models