Vocal effort compensation for MFCC feature extraction in a shouted versus normal speaker recognition task.
Emma JokinenRahim SaeidiTomi KinnunenPaavo AlkuPublished in: Comput. Speech Lang. (2019)
Keyphrases
- speaker recognition
- mel frequency cepstral coefficients
- speech signal
- feature extraction
- speaker identification
- gaussian mixture model
- speaker verification
- speech recognition
- acoustic features
- vector quantization
- probabilistic neural network
- automatic speech recognition
- feature vectors
- image classification
- feature selection
- noisy environments
- pattern classification
- language identification
- emotion recognition
- non stationary
- support vector machine svm
- multiscale
- feature space
- pattern recognition
- wavelet transform
- low level
- audio visual
- image processing
- extracted features
- dimension reduction
- hidden markov models