Author

Carlos Muñoz-Romero

h-index 2 View on Semantic Scholar

We have 1 of 3 papers

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.

Jul 2026

Zero-Shot Face-to-Speech Synthesis via Latent Space Adaptation of a Style-Diffusion TTS Model

This work proposes a Face-to-Speech (F2S) framework that predicts a plausible voice from a static facial image, and develops a lightweight Face Adapter that aligns face-recognition features with the style space of a frozen StyleTTS 2 model, kept frozen during training.

Carlos Muñoz-Romero, Jose A. Gonzalez-Lopez · arXiv.org · 0 citations