RV-TTS synthesizes speech whose voice matches a face image, including artistic portraits, with natural-language control over pace, noise, distance, tone, and recording place.
Dataset We employ audio-visual speech dataset, LRS3 and V oxCeleb2, and audio-only high-quality speech dataset, LibriTTS-R, to train RV-TTS
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Revival with Voice: Multi-modal Controllable Text-to-Speech Synthesis
RV-TTS synthesizes speech whose voice matches a face image, including artistic portraits, with natural-language control over pace, noise, distance, tone, and recording place.