A Deep Learning Based Binaural Speech Enhancement Approach with Spatial Cues Preservation.

Xingwei Sun Risheng Xia Junfeng Li Yonghong Yan

Published in: ICASSP (2019)

Keyphrases

deep learning
speech enhancement
unsupervised learning
noisy environments
machine learning
noise reduction
signal to noise ratio
mental models
speech signal
weakly supervised
spatial information
single channel
linear prediction
prior knowledge
transfer function
multi channel
vocal tract