A linguistically-motivated speaker recognition front-end through session variability compensated cepstral trajectories in phone units.
Joaquin Gonzalez-RodriguezJavier Gonzalez-DominguezJavier Franco-PedrosoDaniel RamosPublished in: ICASSP (2012)
Keyphrases
- speaker recognition
- linguistically motivated
- speaker verification
- speech recognition
- co occurrence
- gaussian mixture model
- speaker identification
- natural language
- linguistic knowledge
- vector quantization
- noun phrases
- probabilistic neural network
- noisy environments
- speech signal
- pattern classification
- language identification
- pattern recognition
- classification accuracy
- multiscale
- hidden markov models
- em algorithm
- language model