Combining voiceprint and face biometrics for speaker identification using SDWS.
Dongdong LiYingchun YangZhaohui WuPublished in: INTERSPEECH (2005)
Keyphrases
- speaker identification
- face biometrics
- gaussian mixture model
- speech recognition
- speech signal
- broadcast news
- noisy environments
- feature extraction
- face recognition
- automatic speech recognition
- machine learning
- computer vision
- non stationary
- real time
- maximum likelihood
- pattern recognition
- feature selection
- neural network