Removing reverberation from audio signals
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Real-world audio recordings are often degraded by factors such as noise, reverberation, and equalization distortion.
Ranked #8 on Speech Enhancement on DEMAND
Recently, deep neural networks (DNNs) have been successfully used for speech enhancement, and DNN-based speech enhancement is becoming an attractive research area.
We investigate the recently proposed Time-domain Audio Sep-aration Network (TasNet) in the task of real-time single-channel speech dereverberation.
Ranked #12 on Speech Separation on wsj0-2mix
First, we study the effectiveness of different dereverberation networks (the generator in GAN) and find that LSTM leads a significant improvement as compared with feed-forward DNN and CNN in our dataset.