Improving the Gap in Visual Speech Recognition Between Normal and Silent Speech Based on Metric Learning.
Sara KashiwagiKeitaro TanakaQi FengShigeo MorishimaPublished in: INTERSPEECH (2023)
Keyphrases
- metric learning
- visual speech recognition
- speech recognition
- distance metric
- hidden markov models
- visual speech
- semi supervised
- lip reading
- learning tasks
- pairwise
- dimensionality reduction
- distance function
- multi task
- speaker identification
- feature space
- pattern recognition
- speech signal
- semi supervised learning
- face recognition
- image matching
- broadcast news
- video sequences