Improved Speech Enhancement with the Wave-U-Net

27 Nov 2018Craig MacartneyTillman Weyde

We study the use of the Wave-U-Net architecture for speech enhancement, a model introduced by Stoller et al for the separation of music vocals and accompaniment. This end-to-end learning method for audio source separation operates directly in the time domain, permitting the integrated modelling of phase information and being able to take large temporal contexts into account... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Speech Enhancement DEMAND Wave-U-Net PESQ 2.4 # 16
CSIG 3.52 # 6
CBAK 3.24 # 5
COVL 2.96 # 6
SSNR 9.97 # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet