An approach to under-determined speech separation based on a non-linear mixture of beamformers.

Mohammad A. Dmour Michael E. Davies

Published in: EUSIPCO (2009)

Keyphrases

blind separation
speech recognition
mixture model
audio visual
pattern recognition
expectation maximization
speech synthesis
real time
speech signal
language acquisition
speaker recognition
gaussian mixture
latent variable models
text to speech
speech recognizer
recognition engine