1

The effect of background noise on speech recognition is not good.

Are there libs or APIs for removing background noise from voice input?

Ideally language-agnostic or tuned for the top 100+ languages, fast enough for real-time, callable from Python or NodeJS.

3

Take a look at 2Hz Noise Suppression API.

It's language-agnostic and is a REST API so you can use it from any programming language.

Currently the API isn't designed for real time however this will be added down the road.

(full disclosure - I work at 2Hz)

| improve this answer | |
  • 1
    Thanks. What is the approximate latency and does it depend on the request size? What is the pricing, are there tiers or volume discounts? – Adam Bittlingmayer Sep 28 '18 at 12:55
  • 1
    The API is designed to work with files at the moment. It receives a file, processes and returns it back. When we add "Near-Real-Time" functionality the latency will be around 20ms for Noise Suppression. Pricing is TBD for now. The API is in Preview. We are happy to give you access if you are interested. – davitb Oct 1 '18 at 6:10
2

Removing noise usually corrupts the speech and harms the performance. It is frequently more accurate to decode noisy speech than noise-cleaned speech, in particular because recognizer does noise cleaning or noise compensation by itself.

For other cases except speech recognition, rnnnoise is reasonable.

| improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.