Joint Sound Source Separation and Speaker Recognition.
Jeroen ZegersHugo Van hammePublished in: INTERSPEECH (2016)
Keyphrases
- speaker recognition
- source separation
- gaussian mixture model
- blind source separation
- vector quantization
- independent component analysis
- speaker verification
- speaker identification
- speech signal
- audio features
- probabilistic neural network
- denoising
- single channel
- sound source
- temporal structure
- speech recognition
- neural network
- image segmentation
- image compression
- pattern recognition
- signal to noise ratio
- non stationary
- em algorithm
- machine learning