Skip to content

Evaluate noise suppression models for required ops #66

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
anssiko opened this issue Jun 4, 2020 · 8 comments · Fixed by #95
Closed

Evaluate noise suppression models for required ops #66

anssiko opened this issue Jun 4, 2020 · 8 comments · Fixed by #95

Comments

@anssiko
Copy link
Member

anssiko commented Jun 4, 2020

Noise suppression use case was adopted by WebNN API in #61 (thanks @ibelem!):

https://webmachinelearning.github.io/webnn/#usecase-noise-suppression

This issue is to discuss the next steps:

  • Evaluate RNNoise model for required ops, to be added to the first-wave models
  • Gauge PoC interest, possible collaboration with related groups e.g. WebRTC
  • Sharing resources, e.g. RNNoise paper and demo
@kdavis-mozilla
Copy link

Hey @jmvalin your work is coming up yet again!

@wchao1115, the WebNN API spec co-editor, was interested in exploring RNNoise a bit further in this context. So, to connect the dots, I thought it apropos to ping you here if any RNNoise questions arise, as, after all, you know more about RNNoise than anyone.

@jmvalin
Copy link

jmvalin commented Jun 17, 2020

@wchao1115 @kdavis-mozilla @anssiko Sure, let me know how I can help.

@wchao1115
Copy link
Collaborator

Thanks @anssiko, @kdavis-mozilla, and @jmvalin. In addition to RNNoise I'd also like to propose NSNet, the baseline model for the Interspeech DNS Challenge.

@wchao1115
Copy link
Collaborator

@jmvalin. From the implementation standpoint, both RNNoise and NSNet are hybrid DSP/ML based solution. Given that webnn is focusing on the deep learning part, how do you see the solution integrated into the web platform, especially on the signal processing part?

I'm not up to date on the state of Web Audio implementation in the web browsers; do you think the level of support for FFT windowing in the browser is sufficient for RNNoise?

@jmvalin
Copy link

jmvalin commented Jun 26, 2020

I don't actually know the state of DSP in the browser. Being able to compute an FFT would certainly be nice, but it's not a showstopper. Similarly, having fast kernels for convolutions/correlations would be equally useful since RNNoise performs pitch analysis. Honestly what I've like to see at some point is a WebBLAS (plus FFT and convolution/correlation). That would probably cover most use cases -- including a big chunk of WebML.

@wchao1115
Copy link
Collaborator

To date, we still need to define split and clamp to satisfy the model's requirements.

@huningxin
Copy link
Contributor

To date, we still need to define split and clamp to satisfy the model's requirements.

+1. And the clamp op would be useful to other first-wave models. For instance, when working on the MobileNet example, I found the TFLite version has the Relu6 op. According to the TensorFlow implementation, it can be lowered to XLA Clamp op.

@wchao1115 , if no duplication, I can work on a PR to add the split and clamp ops. Please let me know.

@wchao1115
Copy link
Collaborator

Sounds good. Thanks @huningxin

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging a pull request may close this issue.

5 participants