Ye Gao
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
NLP×1
Frequent co-authors
Research Timeline
2026
Sparse Autoencoders for Interpretable Emotion Control in Text-to-Speech
The paper uses sparse autoencoders to identify specific latent features within LLM-based TTS models, enabling interpretable and fine-grained control over emotional expression by intervening in small subsets of these features.
Highlighted terms show continued research focus across papers
Papers
cs.CLRecentMay 31, 2026
Sparse Autoencoders for Interpretable Emotion Control in Text-to-Speech
Hongfei Du, Jiacheng Shi, Sidi Lu, Gang Zhou +1 more
The paper uses sparse autoencoders to identify specific latent features within LLM-based TTS models, enabling interpretable and fine-grained control over emotional expression by intervening in small s…
View →