conftrace_

video-to-speech synthesis

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

mel-frequency spectrogram (1) spectrogram prediction (1) speaker characteristics (1) lip reading (1) visual speech (1) acoustic feature (1) neural vocoder (1) self-supervised pretraining (1) diffusion model (1) hierarchical representation (1)

Papers

DiVISe: Direct Visual-Input Speech Synthesis Preserving Speaker Characteristics And Intelligibility NAACL 2025 From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech CVPR 2025 DiffV2S: Diffusion-Based Video-to-Speech Synthesis with Vision-Guided Speaker Embedding ICCV 2023 SVTS: Scalable Video-to-Speech Synthesis Interspeech 2022