Skip to content
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

Test Amazon Voice Focus noise suppression as a command line tool #2176

Open
hassanctech opened this issue Apr 20, 2022 · 7 comments
Open

Test Amazon Voice Focus noise suppression as a command line tool #2176

hassanctech opened this issue Apr 20, 2022 · 7 comments
Labels
audio-ml Machine learning features on audio stream such as voice focus and echo reduction feature-request New feature or request Triaged

Comments

@hassanctech
Copy link

What are you trying to do?

I'm like to test out the Amazon Voice Focus noise suppression / echo cancellation and compare side by side with rnnoise and/or other offerings. Today I see it's integrated as part of the Chime SDK, do you have this available as a command line tool for quick testing a file with noise against Amazon Voice Focus to get an idea for its quality and how it stacks up against other offerings? This is a good way for us to see a "before" and "after" comparison with and without the noise suppression.

How can the documentation be improved to help your use case?

Providing an easy way to test out the noise suppression (I know there is a browser sample which can be run which actually starts/joins a meeting) but a command line tool would be easier/faster.

What documentation have you looked at so far?

@LeviSklaroff LeviSklaroff added the audio-ml Machine learning features on audio stream such as voice focus and echo reduction label Apr 20, 2022
@hassanctech
Copy link
Author

Another follow-up here so I went on a Chime Meeting using the desktop application (with the voice focus enabled) and at least with my short test it appears to be vastly superior to rnnoise so I'm pretty excited about the idea of using it. Now the question is are there plans to vend it as a separate library and/or do you see any issues with someone doing that who is not using AWS Chime (backend)?

@hassanctech
Copy link
Author

I see you have this: https://aws.amazon.com/blogs/business-productivity/using-amazon-voice-focus-ami-to-reduce-noise-in-audio/

But I'd really like to know if it's possible and are there any issues with using this complete independently from Chime itself? Suppose we have an entirely different application could we use your noise suppression? If it isn't free to use that way then do you allow others to license it?

@devalevenkatesh
Copy link
Contributor

Hi @hassanctech , Thanks for your interest in the Amazon Chime SDK and the Voice Focus feature. Tagging
@richhx if he can provide more insights on this.

@devalevenkatesh devalevenkatesh added the feature-request New feature or request label Apr 22, 2022
@hassanctech
Copy link
Author

Yeah any insight you can provide would be helpful!

@richhx
Copy link
Member

richhx commented Apr 25, 2022

Hi @hassanctech, sorry for the late reply (I had / still have COVID). We are looking into licensing approaches to use the Voice Focus noise suppression for JavaScript. In the meantime, I would recommend that you use the AMI approach linked in the blog if you would like to use a CLI. The AMI offers a library and simple script that offers processing file inputs/outputs using the library so you can use it more quickly from the command-line. If you have any questions about that, happy to help out.

@hassanctech
Copy link
Author

Thanks @richhx sorry to hear about the COVID, I hope you have a quick/complete recovery!

That's cool if you could keep us updated on the licensing approaching to use voice focus that would be awesome!

@richhx
Copy link
Member

richhx commented Apr 26, 2022

For sure, I will definitely keep you up to date on that :)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
audio-ml Machine learning features on audio stream such as voice focus and echo reduction feature-request New feature or request Triaged
Projects
None yet
Development

No branches or pull requests

5 participants