Landmark-Guided Cross-Speaker Lip Reading with Mutual Information Regularization.
Linzhi WuXingyu ZhangYakun ZhangChangyan ZhengTiejun LiuLiang XieYe YanErwei YinPublished in: CoRR (2024)
Keyphrases
- mutual information
- lip reading
- speaker identification
- image registration
- visual speech
- speech recognition
- head tracking
- gaussian mixture model
- expression recognition
- similarity measure
- feature selection
- feature extraction
- speech signal
- speaker verification
- audio visual
- maximum likelihood
- hidden markov models
- automatic speech recognition
- broadcast news
- image analysis
- audio signals
- image processing
- feature vectors