Localization based stereo speech separation using deep networks.

Yang Yu Wenwu Wang Jian Luo Pengming Feng

Published in: DSP (2015)

Keyphrases

speech recognition
social networks
computer vision
stereo vision
three dimensional
depth map
spoken language
audio visual
speech signal
early vision
recognition engine
real time
omni directional
disparity estimation
sound source
complex networks
stereo matching
ground truth
pattern recognition