Improving Robustness of Speaker Recognition in Noisy and Reverberant Conditions via Training.
Ahmed H. Al-NooriKhamis A. Al-KarawiFrancis F. LiPublished in: EISIC (2015)
Keyphrases
- speaker recognition
- speech signal
- noisy environments
- gaussian mixture model
- speaker identification
- vector quantization
- speech recognition
- speaker verification
- probabilistic neural network
- training set
- maximum likelihood
- multi modal
- unsupervised learning
- neural network
- sentiment analysis
- supervised learning
- semi supervised
- emotion recognition