Microsoft Teams now uses AI to improve echo, interruptions, and audio

Microsoft has spent the past two years adding flashy new productivity features to Teams, and the company is now overhauling how the basics work thanks to artificial intelligence. We’ve all been on a call where someone has bad room acoustics making it hard to hear, or watched two people try to talk at the same time creating an awkward “no, go ahead” moment. New AI-powered sound quality improvements from Microsoft should improve or even eliminate these everyday annoyances.

Microsoft is now using machine learning models to improve room acoustics so you don’t sound like you’re hiding in a cave. “While we’ve been doing our best with digital signal processing to do a really good job in Teams, we’re now starting to use machine learning for the first time to build echo cancellation where you can really reduce echo from all the different devices,” explains Robert Eichner, Lead Program Manager for Smart Conversations. and cloud communications at Microsoft, in an interview with the edge.

Microsoft has been testing this for several months, measuring their models in the real world to make sure that Teams users notice reduced echo and improvements in call quality. The software maker has used 30,000 hours of talk to help train its models, and has captured thousands of devices through crowdsourcing where Teams users are paid to record their voice and play audio from their devices.

“We also simulate about 100,000 different rooms…room acoustics play a big role in echo cancellation,” says Aichner. The result is significant improvements in call sound quality, eliminating echo which also allows multiple people to speak at the same time. You can see all the improvements in action in the video above.

If Teams detects that audio is bouncing or reverberating in a room resulting in shallow sound, the model will also transform and process the captured audio to make it sound as if Teams participants are speaking into a near-field microphone rather than an echo mess.

The most impressive part is the ability for people to interrupt each other on Teams calls now, without the awkward interference where you can’t hear the other person because of the echo. Microsoft is now shipping all of this work in Teams, along with improvements it made with its previously AI-based noise cancellation system. All processing is done locally on the client’s machines, rather than in the cloud.

“We said we want to do this on the client, because the cloud is still very expensive if you want to make every call that is processed in the cloud… and obviously we will have to pass that cost on to the client,” Aichner explains. That could mean that these important Teams improvements are restricted to paying customers, and On-Device Path means features like noise suppression are available on 90 percent of devices that use Teams.

All new Microsoft Teams improvements are live, along with some real-time screen improvements for text in videos and AI-based improvements for bandwidth limitations during video calls or screen sharing.

Leave a Comment