Generating Intelligible Audio Speech From Visual Speech.
Thomas Le CornuBen MilnerPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2017)
Keyphrases
- visual speech
- hidden markov models
- speaker identification
- visual speech recognition
- audio visual speech recognition
- speech signal
- noisy environments
- audio signals
- lip reading
- video signals
- acoustic features
- broadcast news
- speech recognition
- audio signal
- text to speech
- speaker verification
- gaussian mixture model
- cepstral coefficients
- feature selection