TCD-TIMIT
Emerging5papers using it
2021first seen
Papers using TCD-TIMIT (5)
- Audio-Visual Speech Separation via Bottleneck Iterative NetworkOn the Audio-visual Synchronization for Lip-to-Speech SynthesisLipSound2: Self-Supervised Pre-Training for Lip-to-Speech Reconstruction
and Lip ReadingAudio-Visual Speech Separation in Noisy Environments with a Lightweight
Iterative ModelRobustL2S: Speaker-Specific Lip-to-Speech Synthesis exploiting
Self-Supervised Representations