Distributed Microphone Speech Enhancement based on Deep Learning

TL;DR

This paper explores three deep neural network-based speech enhancement systems in distributed microphone setups, demonstrating improved speech quality and intelligibility in noisy environments, with the channel-dependent fusion system performing best.

Contribution

It introduces and compares three novel DNN-based speech enhancement architectures for distributed microphone arrays, highlighting the effectiveness of channel-dependent fusion.

Findings

All three DNN systems improve speech quality and intelligibility.

The channel-dependent DNN fusion system achieves the highest SNR improvement.

Experimental results validate the effectiveness of the proposed methods.

Abstract

Speech-related applications deliver inferior performance in complex noise environments. Therefore, this study primarily addresses this problem by introducing speech-enhancement (SE) systems based on deep neural networks (DNNs) applied to a distributed microphone architecture, and then investigates the effectiveness of three different DNN-model structures. The first system constructs a DNN model for each microphone to enhance the recorded noisy speech signal, and the second system combines all the noisy recordings into a large feature structure that is then enhanced through a DNN model. As for the third system, a channel-dependent DNN is first used to enhance the corresponding noisy input, and all the channel-wise enhanced outputs are fed into a DNN fusion model to construct a nearly clean signal. All the three DNN SE systems are operated in the acoustic frequency domain of speech signals in a diffuse-noise field environment. Evaluation experiments were conducted on the Taiwan Mandarin Hearing in Noise Test (TMHINT) database, and the results indicate that all the three DNN-based SE systems provide the original noise-corrupted signals with improved speech quality and intelligibility, whereas the third system delivers the highest signal-to-noise ratio (SNR) improvement and optimal speech intelligibility.