Name
Title | ||
|---|---|---|
Noise Prior Knowledge Learning for Speech Enhancement via Gated Convolutional Generative Adversarial Network |
Abstract | ||
|---|---|---|
Speech enhancement generative adversarial network (SEGAN) is an end-to-end deep learning architecture, which only uses the clean speech as the training targets. However, when the signal-to-noise ratio (SNR) is very low, predicting clean speech signals could be very difficult as the speech is dominated by the noise. In order to address this problem, in this paper, we propose a gated convolutional neural network (CNN) SEGAN (GSEGAN) with noise prior knowledge learning to address this problem. The proposed model not only estimates the clean speech, but also learns the noise prior knowledge to assist the speech enhancement. In addition, gated CNN has an excellent potential for capturing long-term temporal dependencies than regular CNN. Motivated by this, we use a gated CNN architecture to acquire more detailed information at waveform level instead of regular CNN. We evaluate the proposed method GSEGAN on Voice Bank corpus. Experimental results show that the proposed method GSEGAN outperforms the SEGAN baseline, with a relative improvement of 0.7%, 28.2% and 43.9% for perceptual evaluation of speech quality (PESQ), overall Signal-to-Noise Ratio (SNRovl) and Segmental Signal-to-Noise Ratio (SNRseg), respectively. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/APSIPAASC47483.2019.9023216 | 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) |
Keywords | DocType | ISSN |
gated convolutional generative adversarial network,speech enhancement generative adversarial network,end-to-end deep learning architecture,GSEGAN,gated CNN architecture,speech quality,segmental signal-to-noise ratio,noise prior knowledge learning,clean speech signals prediction,long-term temporal dependencies,SEGAN baseline,SNRseg,SNRovl,overall signal-to-noise ratio,voice bank corpus | Conference | 2640-009X |
ISBN | Citations | PageRank |
978-1-7281-3249-5 | 0 | 0.34 |
References | Authors | |
6 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Cunhang Fan | 1 | 2 | 3.79 |
| Bin Liu | 2 | 191 | 35.02 |
| Jianhua Tao | 3 | 848 | 138.00 |
| Jiangyan Yi | 4 | 19 | 17.99 |
| Zhengqi Wen | 5 | 86 | 24.41 |
| Ye Bai | 6 | 0 | 0.34 |