Speech Source Separation by Combining Localization Cues with Mixture Models of Speech Spectra.

Published in: ICASSP (1) (2007)

Keyphrases

mixture model
speech recognition
gaussian mixture model
source separation
generative model
language model
audio visual
speech signal
em algorithm
model selection
unsupervised learning
probabilistic model
maximum likelihood
expectation maximization
multimedia
text mining
audio features
feature vectors