Phase-aware Speech Enhancement with Deep Complex U-Net

Most deep learning-based models for speech enhancement have mainly focused on estimating the magnitude of spectrogram while reusing the phase from noisy speech for reconstruction. This is due to the difficulty of estimating the phase of clean speech... (read more)

PDF Abstract ICLR 2019 PDF ICLR 2019 Abstract

Datasets


Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
Speech Enhancement DEMAND Large-DCUnet-20-Layer-cRMCn PESQ 3.24 # 1
Speech Enhancement DEMAND DCUnet-10-Layer-cRMCn PESQ 2.72 # 14
Speech Enhancement DEMAND DCUnet-16-Layer-cRMCn PESQ 2.93 # 10
Speech Enhancement DEMAND DCUnet-20-Layer-cRMCn PESQ 3.13 # 4

Methods used in the Paper


METHOD TYPE
Concatenated Skip Connection
Skip Connections
ReLU
Activation Functions
Max Pooling
Pooling Operations
Convolution
Convolutions
U-Net
Semantic Segmentation Models