GLD-Net: Improving Monaural Speech Enhancement by Learning Global and Local Dependency Features with GLD Block

TL;DR

GLD-Net enhances monaural speech quality by integrating global and local dependency features through GLD blocks, leading to superior performance over existing methods in speech enhancement tasks.

Contribution

This paper introduces the GLD block for capturing long-term dependencies at global and local levels, improving speech enhancement in a novel encoder-decoder framework.

Findings

GLD-Net outperforms state-of-the-art methods in PESQ and STOI metrics.

GLD blocks effectively model long-term dependencies in spectrograms.

The proposed network improves speech quality and intelligibility.

Abstract

For monaural speech enhancement, contextual information is important for accurate speech estimation. However, commonly used convolution neural networks (CNNs) are weak in capturing temporal contexts since they only build blocks that process one local neighborhood at a time. To address this problem, we learn from human auditory perception to introduce a two-stage trainable reasoning mechanism, referred as global-local dependency (GLD) block. GLD blocks capture long-term dependency of time-frequency bins both in global level and local level from the noisy spectrogram to help detecting correlations among speech part, noise part, and whole noisy input. What is more, we conduct a monaural speech enhancement network called GLD-Net, which adopts encoder-decoder architecture and consists of speech object branch, interference branch, and global noisy branch. The extracted speech feature at global-level and local-level are efficiently reasoned and aggregated in each of the branches. We compare the proposed GLD-Net with existing state-of-art methods on WSJ0 and DEMAND dataset. The results show that GLD-Net outperforms the state-of-the-art methods in terms of PESQ and STOI.