Mobile Device-Based Speech Enhancement System Using Lip-Reading.
Tomonori NakaharaKohei FukuyamaMitsuru HamadaKenji MatsuiYoshihisa NakatohYumiko O. KatoAlberto RivasJuan Manuel CorchadoPublished in: DCAI (2020)
Keyphrases
- lip reading
- speech enhancement
- noisy environments
- speaker identification
- speech signal
- noise reduction
- signal to noise ratio
- visual speech
- single channel
- head tracking
- expression recognition
- speech recognition
- vocal tract
- linear prediction
- multi channel
- image segmentation
- computer vision
- facial expression recognition
- frequency domain
- human computer interaction
- image compression
- language model
- multiresolution
- multimedia