Google is using machine learning to deal with packet loss of audio data on its video calling app.
The feature’s already available on Pixel 4 devices via the December feature drop.
Other as-yet-unnamed phones are also slated to receive the same tech in the future.
Google’s Duo is already « the best video calling service you can use » – even Samsung, it seems, has seen the light – but the company doesn’t just stay in its designated areas with the constant stream of new features.
The latest innovations from Google on this should also be impressive, as the company uses machine learning algorithms to deal with packet loss (where data is lost as it travels across the internet) by measuring what audio losses have been (via The Verge).
While such technology already exists, Google’s launch, the brainchild of its DeepMind subsidiary, is far better than its competitors and can double the larger amount of lost audio, the company says. It has also been trained to work in 48 different languages.
The company notes that about 99% of all Duo calls receive at least packet loss, with 10% of calls losing 8% of audio data. This technology can help improve the audio quality of Duo phones, especially in developing countries, where the internet connection is unstable. In addition, all the processing is done on the device, which means your privacy is protected and the feature respects the end-to-end encryption of the Duo.
Google says it has already enabled Duo tech on the Pixel 4 with the December feature icon, and plans to expand its availability to other phones. It did not, unfortunately, provide the names of these calls.
Did you listen to this week’s Android Central Podcast?
Every week, the Android Central Podcast brings you the latest tech news, analytics and hot takeaways, with regular participants and special guests.
Subscribe to Pocket Casts: Audio
Subscribe to Spotify: Audio
Subscribe to iTunes: Audio