Softsad: Integrated frame-based speech confidence for speaker recognition.

Mitchell McLaren Martin Graciarena Yun Lei

Published in: ICASSP (2015)

Keyphrases

speaker recognition
gaussian mixture model
speaker verification
vector quantization
speaker identification
probabilistic neural network
speech recognition
speech signal
maximum likelihood
self organizing maps
mel frequency cepstral coefficients
probabilistic model
model selection
mixture model