All termsGlossary

What is noise suppression?

Noise suppression is audio processing that reduces background sound on a call, such as traffic, keyboards or other people talking, while keeping the speaker’s voice clear.

Why it matters

Customers call from cars, shops and busy streets, and agents often work in shared rooms. Background noise makes people repeat themselves and causes speech recognition to mishear words, which leads to wrong actions later in the call. Cleaner audio improves the conversation for both sides and makes transcripts and recordings more reliable for later review.

How it works

The processing runs on the audio stream as the call happens. Older methods estimate the steady noise in the signal, such as a fan, and subtract it. Newer methods use a model trained on many examples of speech and noise to separate the two, which also handles sudden sounds. The work must take only a few milliseconds, or it adds delay to the call.

Example

A customer phones a breakdown service from the side of a motorway. Without processing, passing traffic drowns out parts of the registration number and the voice agent asks for it three times. With noise suppression applied to the incoming audio, the traffic is reduced to a low hum, the registration is recognised first time and a recovery vehicle is booked.

Get Started

Let’s build AI agents, together.

Talk with us to see the top three use cases for AI agents at your business, and how quickly you could go live.

Live in 7 days · Works inside the tools your team already uses · Hands off with full context