papers AI Learner
The Github is limit! Click to go to the new site.

RHR-Net: A Residual Hourglass Recurrent Neural Network for Speech Enhancement

2019-04-15
Jalal Abdulbaqi, Yue Gu, Ivan Marsic

Abstract

Most current speech enhancement models use spectrogram features that require an expensive transformation and result in phase information loss. Previous work has overcome these issues by using convolutional networks to learn long-range temporal correlations across high-resolution waveforms. These models, however, are limited by memory-intensive dilated convolution and aliasing artifacts from upsampling. We introduce an end-to-end fully-recurrent hourglass-shaped neural network architecture with residual connections for waveform-based single-channel speech enhancement. Our model can efficiently capture long-range temporal dependencies by reducing the features resolution without information loss. Experimental results show that our model outperforms state-of-the-art approaches in six evaluation metrics.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1904.07294

PDF

http://arxiv.org/pdf/1904.07294


Similar Posts

Comments