Effect of multicondition training on i-vector PLDA configurations for speaker recognition.

Padmanabhan Rajan Tomi Kinnunen Ville Hautamäki

Published in: INTERSPEECH (2013)

Keyphrases

speaker recognition
gaussian mixture model
speaker verification
vector quantization
speaker identification
feature vectors
probabilistic neural network
speech recognition
machine learning
training set
multi modal
generative model
audio visual
gaussian process regression