A Comparison of MFCC and LPCC with Deep Learning for Speaker Recognition.
Haiyan YangYanrong DengHua-An ZhaoPublished in: ICBDC (2019)
Keyphrases
- image features
- speaker recognition
- deep learning
- mel frequency cepstral coefficients
- gaussian mixture model
- speaker identification
- vector quantization
- speaker verification
- unsupervised learning
- probabilistic neural network
- speech signal
- speech recognition
- machine learning
- computer vision
- mixture model
- feature extraction
- weakly supervised
- mental models
- generative model
- pattern recognition
- noisy environments
- maximum likelihood