Cancellable template generation for speaker recognition based on spectrogram patch selection and deep convolutional neural networks.
Samia Abd El-MoneimMohamed Abd-Elsalam NassarMoawad I. DessoukyNabil A. IsmailAdel S. El-FishawyFathi E. Abd El-SamiePublished in: Int. J. Speech Technol. (2022)
Keyphrases
- speaker recognition
- convolutional neural networks
- speech signal
- gaussian mixture model
- speech recognition
- speaker identification
- speaker verification
- convolutional network
- vector quantization
- image patches
- probabilistic neural network
- automatic speech recognition
- information retrieval
- mixture model
- edge detection
- hidden markov models
- feature space