Gated Residual Networks With Dilated Convolutions for Monaural Speech Enhancement | IEEE Journals & Magazine | IEEE Xplore

Gated Residual Networks With Dilated Convolutions for Monaural Speech Enhancement


Abstract:

For supervised speech enhancement, contextual information is important for accurate mask estimation or spectral mapping. However, commonly used deep neural networks (DNNs...Show More

Abstract:

For supervised speech enhancement, contextual information is important for accurate mask estimation or spectral mapping. However, commonly used deep neural networks (DNNs) are limited in capturing temporal contexts. To leverage long-term contexts for tracking a target speaker, we treat speech enhancement as a sequence-to-sequence mapping, and present a novel convolutional neural network (CNN) architecture for monaural speech enhancement. The key idea is to systematically aggregate contexts through dilated convolutions, which significantly expand receptive fields. The CNN model additionally incorporates gating mechanisms and residual learning. Our experimental results suggest that the proposed model generalizes well to untrained noises and untrained speakers. It consistently outperforms a DNN, a unidirectional long short-term memory (LSTM) model, and a bidirectional LSTM model in terms of objective speech intelligibility and quality metrics. Moreover, the proposed model has far fewer parameters than DNN and LSTM models.
Page(s): 189 - 198
Date of Publication: 15 October 2018

ISSN Information:

PubMed ID: 31355300

Funding Agency:


References

References is not available for this document.