Multi-view learning of acoustic features for speaker recognition.
Karen LivescuMark StoehrPublished in: ASRU (2009)
Keyphrases
- speaker recognition
- acoustic features
- speaker verification
- speech signal
- noisy environments
- speech recognition
- audio visual
- speaker identification
- emotion recognition
- automatic speech recognition
- language identification
- image processing
- using artificial neural networks
- semi supervised
- visual features
- probabilistic neural network
- classification accuracy
- active learning