Face Landmark-based Speaker-independent Audio-visual Speech Enhancement in Multi-talker Environments.
Giovanni MorroneSonia BergamaschiLuca PasaLuciano FadigaVadim TikhanoffLeonardo BadinoPublished in: ICASSP (2019)
Keyphrases
- audio visual
- digit recognition
- speech enhancement
- speaker independent
- noisy environments
- multi modal
- speech recognition
- sound source
- visual information
- noise reduction
- single channel
- speaker verification
- speech signal
- multimedia
- signal to noise ratio
- speaker identification
- linear prediction
- visual data
- emotion recognition
- neural network
- computer vision
- machine learning
- audio features
- image classification
- similarity measure