Audio version of the article
Google has added a new noise cancellation feature on Google Meet that uses Artificial Intelligence (AI) to cancel out the noise in the background for video calling. The features leverage supervised learning, which entails training an AI model on a labeled data set. This is a gradual rollout, so if you are a G Suite customer, you may not get noise cancellation until later this month. Noise cancellation will hit the web first, with Android and iOS coming later.
This feature was announced in April for G Suite Enterprise and G Suite Enterprise for Education customers. Google is currently rolling out the feature, which should be available for everyone by the end of June. Also called as ‘Denoiser’, the feature will first be available on the web version, followed by a release on the Android and iOS app.
Noise cancellation on Google Meet uses a machine learning model capable of distinguishing between noise and speech. The process involves sending the user’s voice from the device to the Google data centre, where it goes through the machine learning model. Post-processing, the data is re-encrypted and sent back to the Meet call.
While demo Serge Lachapelle, G Suite director of product management shoed how the denoiser works using a snack bag, a clicking pen and rotating a metal object in a glass. The video also shows how the feature is able to cancel the unwanted sound, keeping Lachapelle’s voice clear.
This article has been ublished from a wire agency feed without modifications to the text. Only the headline has been changed.