A new Speech Feature Fusion method with cross gate parallel CNN for Speaker Recognition.
Jiacheng ZhangWenyi YanYe ZhangPublished in: CoRR (2022)
Keyphrases
- speaker recognition
- fusion method
- gaussian mixture model
- data fusion
- vector quantization
- information fusion
- speaker verification
- speaker identification
- fusion methods
- probabilistic neural network
- multi sensor
- speech recognition
- speech signal
- image fusion
- feature vectors
- mel frequency cepstral coefficients
- audio visual
- discrete wavelet transform
- pattern recognition
- feature set
- noisy environments
- soft computing
- multiresolution
- multiscale
- neural network