yongxuUSTC
how to use?
This seems like an interesting project. I was wondering if you can just give me a quick rundown on how to use this framework to denoise 44.1kHz wav mixtures? From training to enhancement. Thank you!
You can downsample your 44.1khz wav into 16khz waveform, and then you can use my trained model to enhance your noisy wav:
Model and Matlab enhancement code: (run on windows only) https://drive.google.com/file/d/0B5r5bvRpQ5DRR1lIV1hpZ0RLQ0E/view
However, if you want to train a model to enhance 44.1khz wav, then it is easy to do that using my code.
GPU code: https://github.com/yongxuUSTC/DNN-for-speech-enhancement python code: https://github.com/yongxuUSTC/sednn
Best regards, yong
Dr. Yong XU https://sites.google.com/view/xuyong/home
From: dankorg Date: 2018-03-25 17:25 To: yongxuUSTC/sednn CC: Subscribed Subject: [yongxuUSTC/sednn] how to use? (#4) This seems like an interesting project. I was wondering if you can just give me a quick rundown on how to use this framework to denoise 44.1kHz wav mixtures? From training to enhancement. Thank you! — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or mute the thread.
I want to use "https://github.com/yongxuUSTC/sednn". How do I use it to denoise 44.1kHz mixtures? I don't want to downsample. I just need some steps, like config, folders, how do I set up the noisy files, do they have to be the same length, how does the actual training work, and then how does the denoising work, like a little guide. The code itself is a little bit confusing.
Thank you
hi @yongxuUSTC , i tried to use you model but i got stuck. i follow the readme.text and insert my noisy audio into wav_lsp folder but it couldn't run. Can you tell me how to create the .lsp file and more detailed instruction to use your model for my own audio file? thankyou very much
