The 'Audio-Visual Face Cover Corpus': Investigations into audio-visual speech and speaker recognition when the speaker's face is occluded by facewear.
Natalie FecherPublished in: INTERSPEECH (2012)
Keyphrases
- audio visual
- person authentication
- speaker recognition
- speaker verification
- visual speech
- speaker identification
- multi modal
- audio visual speech recognition
- visual information
- emotion recognition
- audio features
- visual data
- multimedia
- hidden markov models
- multi stream
- noisy environments
- speech signal
- gaussian mixture model
- face recognition
- language identification
- facial images
- acoustic features
- mel frequency cepstral coefficients
- feature extraction