语音增强资料

 

[1]S. Pascual, A. Bonafonte, and J. Serrà. Implementation of SEGAN:
Speech Enhancement Generative Adversarial Network. 2019. URL:
 https://github.com/santi-pdp/segan.
[2]D. Rethage, J. Pons, and X. Serra. Implementation of A Wavenet
for Speech Denoising. 2019. URL: https : / / github . com /
drethage/speech-denoising-wavenet.
[3]ododoyo. Partial implementation of Convolutional-Recurrent Neural
Networks for Speech Enhancement. 2019. URL: https://github.
com/ododoyo/EHNet.
[4] Jingdong Li. A python package for calculating the PESQ. 2019. URL:
https://github.com/vBaiCai/python-pesq.
[5] Cees Taal. STOI – Short-Time Objective Intelligibility Measure. 2019.
URL: http://www.ceestaal.nl/code/.
[6] Oscar Xing Luo. Human evaluation spreadsheet. 2019. URL:
https://drive.google.com/file/d/1XnguF_eHwKyogMQotkkxXSSae_w3zZp/view?usp=sharing.
[7] Esfandiar Zavarehei. Wiener Filter. 2019. URL: https : / /
mathworks.com/matlabcentral/fileexchange/7673-
wiener-filter.
 

 

摘自一篇语音增强的研究的报告，主要包括SEGAN、Wavenet等方法，文章：“A Study on WaveNet, GANs and General CNNRNN Architectures”