Demos
1 Neural Spatio-Temporal Beamformer for Target Speech Separation (complex-valued mask based multi-tap MVDR jointly trained with deep learning method for multi-channel multi-modal target speech separation) DEMO:
https://yongxuustc.github.io/mtmvdr/
2 DNN-based speech enhancement demos:
http://staff.ustc.edu.cn/~jundu/The%20team/yongxu/demo/SE_DNN_taslp.html
http://staff.ustc.edu.cn/~jundu/The%20team/yongxu/demo/IS15.html
Third -party test/verified DNN-based speech enhancement demos : links (by other people around the world)
3 DNN based speech enhancement tool is open now and can be downloaded at:
https://drive.google.com/file/d/0B5r5bvRpQ5DRR1lIV1hpZ0RLQ0E/view
https://github.com/yongxuUSTC/DNN-for-speech-enhancement
4 Easiest deep learning based speech enhancement code using keras
https://github.com/yongxuUSTC/deep_learning_based_speech_enhancement_keras_python
5 My Github website: https://github.com/yongxuUSTC
6 Attention and Localization for audio tagging demo:
https://sites.google.com/view/xuyong/demos/attention_model