Question about DNSMOS
Hi, thanks for this work. I have some questions about DNSMOS. I tested the raw blind test set and deepfilter2 results with the DNSMOS tool (https://github.com/microsoft/DNS-Challenge dnsmos.py). Both results are different from your paper. What preprocessing did you do to the blind test set?
How did you test exactly? Please provide code and instructions to reproduce your claims. The paper results are obtained using https://github.com/Rikorose/DeepFilterNet/blob/ac9c803/DeepFilterNet/df/evaluation_utils.py#L199=
Ok i will try this file. My previous tests used this one. python DeepFilterNet/df/enhance.py -m DeepFilterNet2 path/to/noisy_audio.wav The results are then scored by DNSMOS tool.
You could try to to use the -D option to compensate for the STFT delay.