Author

Wen-Ming Tu

View on Semantic Scholar

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... Oct 2025

UltraVoice: Scaling Fine-Grained Style-Controlled Speech Conversations for Spoken Dialogue Models

The first large-scale speech dialogue dataset engineered for multiple fine-grained speech style control, UltraVoice, demonstrates substantial gains in core understanding, reasoning, and conversational abilities, and its utility extends to training controllable Text-to-Speech (TTS) models.

Wen-Ming Tu, Guanrou Yang, Rui-Qi Yan et al. · arXiv.org · 3 citations · ⚡1