i-Vector Transformation Using a Novel Discriminative Denoising Autoencoder for Noise-Robust Speaker Recognition.
Shivangi MahtoHitoshi YamamotoTakafumi KoshinakaPublished in: INTERSPEECH (2017)
Keyphrases
- speaker recognition
- denoising
- noisy environments
- speaker verification
- gaussian noise
- gaussian mixture model
- image denoising
- denoising methods
- vector quantization
- noise level
- image processing
- speaker identification
- natural images
- noisy images
- signal to noise ratio
- speech signal
- noise reduction
- speech recognition
- neural network
- pattern recognition
- feature extraction
- probabilistic neural network
- image segmentation
- learning algorithm