Lights, Camera, Sound - AI Improvements to Google Meet
Written by Sue Gee   
Friday, 13 May 2022

Updates and new features in Google Meet which will bring welcome improvements to virtual meetings were announced this week at Google I/O.

As a "hybrid" event itself, Google I/O provided a very appropriate platform for introducing upcoming features to Google Workspace which will improve the quality of virtual meetings and facilitate productive remote collaboration. And as icing on the cake Google was able to claim that some of these enhancements are possible thanks to AI. 

Three new features are are intended to overcome the problems of using sub-optimal video recording kit in sub-optimal surroundings. Portrait restore improves video quality by tapping into Google's AI tech to automatically sharpen and touch up your video feed and will help in situations where Google Meet is used in rooms with less than ideal lighting.. It also automatically improves your video in case you have a bad Wi-Fi connection, according to Google. 


Going further in addressing the lighting problem, Portrait light uses machine learning to simulate studio-quality lighting in the user's video feed, enabling them to adjust both the lighting position and the brightness. 

To help with sound quality De-reverberation filters out echoes on Google Meet calls and should be especially useful for those videoconferencing from an empty room or a space with hard surfaces. 

A coming-later-this-year feature that sounds very useful is automated transcriptions of Google Meet meetings to Google Workspace so that people can quickly catch up on meetings they coundlent attend. Presumably this is thanks to speech-to-text AI. Another use of natural language understanding is automatic summaries. The auto-summaries already introduced in Google Docs is now being extended to Spaces to provide a digest of conversations you may have missed.

Google has also announced a Live Sharing SDK that allows developers to sync content across devices in real time and incorporate Meet into their apps. According to the announcement, the SDK supports two key use cases:

  • Co-Watching—Syncs streaming app content across devices in real time, and allows users to take turns sharing videos and playing the latest hits from their favorite artist. This allows for users to share controls such as starting and pausing a video, or selecting new content in the app.
  • Co-Doing—Syncs arbitrary app content, allowing users to get together to perform an activity like playing video games or follow the same workout regime.

The Google Meet Live Sharing SDK is now in preview and you can apply for access through the Early Access Program.



More Information

7 ways AI is making Google Workspace better

Introducing the Google Meet Live Sharing SDK

Related Articles

Google AI Recreates Lost Klimt Artworks

Google Releases Forms API

To be informed about new articles on I Programmer, sign up for our weekly newsletter, subscribe to the RSS feed and follow us on Twitter, Facebook or Linkedin.



Vote For The Creepiest Robot

The IEEE has relaunched its Robot Guide website and wants visitors not only to explore its expanded collection but to decide which robots are the most wanted, the coolest and the best. There's also a  [ ... ]

.NET Community Toolkit 8.2 Adds Faster Generators

Microsoft has announced version 8.2 of the .NET Community Toolkit, a collection of helpers and APIs that work for all .NET developers. The developers say this new version includes performance improvem [ ... ]

More News





or email your comment to:

Last Updated ( Friday, 13 May 2022 )