Effective use of DCTS for contextualizing features for speaker recognition.

Mitchell McLaren Nicolas Scheffer Luciana Ferrer Yun Lei

Published in: ICASSP (2014)

Keyphrases

speaker recognition
feature set
low level
feature vectors
feature space
vector quantization
speech recognition
mel frequency cepstral coefficients
image processing
feature extraction
multiresolution
multi modal
probabilistic neural network