Speaker Localization among Multi-faces in noisy Environment by Audio-visual Integration.
Hyun-Don KimJongSuk ChoiMunsang KimPublished in: ICRA (2006)
Keyphrases
- audio visual
- speaker verification
- noisy environments
- audio visual speech recognition
- multi modal
- visual information
- speech recognition
- visual data
- multi stream
- emotion recognition
- noise reduction
- multimedia
- audio features
- speaker identification
- speech signal
- face recognition
- neural network
- face images
- acoustic features
- image segmentation
- multimedia data
- image database
- automatic speech recognition
- input image
- high level