search

facebookresearch / denoiser

Real Time Speech Enhancement in the Waveform Domain (Interspeech 2020)We provide a PyTorch implementation of the paper Real Time Speech Enhancement in the Waveform Domain. In which, we present a causal speech enhancement model working on the raw waveform that runs in real-time on a laptop CPU. The proposed model is based on an encoder-decoder architecture with skip-connections. It is optimized on both time and frequency domains, using multiple loss functions. Empirical evidence shows that it is capable of removing various kinds of background noise including stationary and non-stationary noises, as well as room reverb. Additionally, we suggest a set of data augmentation techniques applied directly on the raw waveform which further improve model performance and its generalization abilities.
Other
1.62k stars 299 forks source link

Reduce noise cancellation degree #141

Closed dgoryeo closed 1 year ago

dgoryeo commented 1 year ago

Is there any way to soften / reduce the amount of denoising? Thanks

adefossez commented 1 year ago

You can pass ´--dry 0.1´ for instance, this will put back 10% of the original signal + 90% of denoised. You can tune this number to your liking.

dgoryeo commented 1 year ago

Hi @adefossez , I'm afraid I'd need to ask for your help again:

I am trying to pass --dry option in a colab python code as:

import denoiser options = {"dry":0.1, "device":"cuda", "noisy_dir":path, "model":model} denoised = denoiser.enhnace(**options)

But I get error message: AttributeError: module 'denoiser' has no attribute 'enhnace'.

Where am I going wrong?

balkce commented 1 year ago

There may be a small typo in the line:

denoised = denoiser.enhnace(**options)

I think it should be:

denoised = denoiser.enhance(**options)

dgoryeo commented 1 year ago

Ouch! Embarassing :) Thanks a lot for looking int it. cheers