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

Microsoft has been adding flashy new productivity features to Teams over the past two years, and now the company is overhauling the fundamentals thanks to AI. We’ve all had a phone conversation where someone has bad room acoustics that make it hard to hear them, or we’ve seen two people trying to talk at the same time, causing an awkward “no, go ahead” moment. Microsoft’s new AI-powered voice quality improvements should improve or even eliminate these everyday annoyances.

Microsoft is now using machine learning models to improve room acoustics so that you no longer sound like you’re hiding in a cave. “While we’ve done our best with digital signal processing to do a really good job in Teams, we’ve now started using machine learning for the first time to build echo cancellation that allows you to really reduce the echo from all different devices. explains Robert Aichner, lead program manager for intelligent conversation and communication cloud at Microsoft, in an interview with The edge

Microsoft has been testing this for months and measuring its models in the real world to ensure Teams users notice the echo reduction and call quality improvements. The software maker used 30,000 hours of speech to help train its models and conquered thousands of devices through crowdsourcing, paying Teams users to record their voice and play audio from their device.

“We’re also simulating about 100,000 different rooms… the room acoustics play a big role in echo cancellation,” Aichner says. The result is a great improvement in the sound quality of conversations and an elimination of echo that allows several people to speak at the same time. You can see all the improvements in action in the video above.

If Teams detects sound bouncing or bouncing off a room, resulting in shallow audio, the model will also convert and process recorded audio to make it sound like Teams participants are speaking into a close-up microphone rather than an echo-like mess .

Most impressive is the ability for people to now interrupt each other during Teams conversations, without the awkward overlap where you can’t hear the other person because of the echo. Microsoft is now delivering all of this work in Teams, in addition to the improvements it has previously made with AI-based noise reduction. All processing is done locally on client devices, rather than in the cloud.

“We said we wanted to do it on the customer, because the cloud is still expensive if you want to do every call in the cloud…and of course we would have to pass that cost on to the customer,” Aichner explains. That would mean these key Teams improvements might be limited to paying customers, and the on-device route means features like noise cancellation are available on 90 percent of the devices using Teams.

All of these new Microsoft Teams improvements are now live, along with some real-time screen optimizations for text in videos and AI-based improvements to bandwidth throttling during video or screen-sharing conversations.

Leave a Comment

Your email address will not be published.