On autoencoders in the i-vector space for speaker recognition.
Timur PekhovskySergey NovoselovAleksei SholohovOleg KudashevPublished in: Odyssey (2016)
Keyphrases
- vector space
- speaker recognition
- gaussian mixture model
- denoising
- vector quantization
- speaker verification
- feature vectors
- speaker identification
- probabilistic neural network
- similarity search
- distance measure
- low dimensional
- speech signal
- speech recognition
- image compression
- mixture model
- data sets
- pattern recognition
- computer vision