Deep Learning Backend for Single and Multisession i-Vector Speaker Recognition.
Omid GhahabiJavier HernandoPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2017)
Keyphrases
- deep learning
- back end
- speaker recognition
- user friendly
- gaussian mixture model
- data management
- machine learning
- vector quantization
- speaker verification
- unsupervised learning
- image segmentation
- probabilistic neural network
- learning algorithm
- feature vectors
- high dimensional
- weakly supervised
- speaker identification
- databases
- neural network