Call quality in Microsoft Teams is getting better using Artificial Intelligence

Kevin Okemwa


Looking for more info on AI, Bing Chat, Chat GPT, or Microsoft's Copilots? Check out our AI / Copilot page for the latest builds from all the channels, information on the program, links, and more!

Microsoft Teams has been on the receiving end when it comes to nifty features, which are all geared toward enhancing its user experience. However, there are some instances where communication may not be as smooth as one would like. But as it now seems, Microsoft has incorporated new AI-powered voice quality improvements that are in place to bridge this gap.

Essentially, by incorporating Artificial Intelligence, Microsoft hopes to do away with these disruptions that tend to break communication during meetings. Microsoft is transitioning from digital signal processing to machine learning, which will assist with echo cancellation, and improve room acoustics as well as interruptions.

Robert Aichner, a principal program manager for intelligent conversation and communications cloud at Microsoft during an interview with The Verge said that “Microsoft has been testing this for months, measuring its models in the real world to ensure Teams users are noticing the echo reduction and improvements in call quality. The software maker used 30,000 hours of speech to help train its models and captured thousands of devices through crowd sourcing where Teams users are paid to record their voice and playback audio from their device.”

Microsoft released a video that highlights the key improvements featured in Microsoft Teams since the incorporation of AI powered general in-call audio enhancements.

Users can now speak at the same time during a meeting without encountering any hitches. This means that you can seek clarification during a meeting without experiencing any overlap which is caused by echoes.

According to the interview:

If Teams detects sound is bouncing or reverberating in a room resulting in shallow audio, the model will also convert captured audio and process it to make it sound like Teams participants are speaking into a close-range microphone instead of an echoey mess.

With that said, Microsoft has already started shipping all this work in Teams, where all the processing will be done locally on client devices instead of the cloud because of the cost implication. Otherwise, Microsoft might be compeled to pass on the cost to the users. “That would mean potentially restricting these important Teams improvements to paying customers, and the on-device route means features like noise suppression are available on 90 percent of devices using Teams,” indicated Aichner.

You can catch all these new improvements on Teams as they have already reached general availability. They also come with real-time screen optimizations for text in videos as well as AI-based improvements to bandwidth constraints during video or screen-sharing calls.