New Teams features use AI and machine learning to improve video and audio experiences


On June 13, Microsoft published many new features on its Teams communication platform, focused on improving its voice and video quality. In particular, these new Teams features include echo cancellation, “de-reverberation”, background noise suppression, “interruptibility” capability, real-time screen optimization, based on AI and brightness and focus filters.

“Disruptive echo effects, poor room acoustics, and choppy video are common issues that hamper effective online calls and meetings,” Microsoft Teams Vice President Nicole Herskowitz said in a statement. addressing the main concerns that drove the development of new Teams features. “Thanks to AI and machine learning, which have become fundamental in our strategy of continuous improvement, we have identified and are now proposing innovative improvements in Microsoft Teams that enhance these audio and video challenges in a way that is both user-friendly and scalable in any environment.

Teams’ new echo cancellation capability isn’t the only feature focused on echo issues users are experiencing when communicating within the platform. Some of the audio features introduced by Microsoft also target other echo-related issues caused by environment and audio devices. For example, the new dereverb function uses a machine learning model that can convert captured audio signals into sound, preventing sound from reverberating or making the user sound like they are talking inside a cave. .

Another feature also solves the issue of echo caused by audio devices placed next to each other. “A natural part of conversation is the ability to interrupt for clarification or validation,” says Herskowitz. “This is accomplished through full-duplex (two-way) audio transmission, allowing users to speak and hear others at the same time. When not using headphones, and especially when using devices where the speaker and microphone are very close to each other, it is difficult to suppress echo while retaining audio full duplex. Microsoft Teams uses a “trained” model with 30,000 hours of speech samples to retain the voices you want while removing unwanted audio cues, resulting in smoother dialogue.

According to Herskowitz, with Teams’ new interruptibility capability, users can engage in fluid exchanges without feeling interrupted or cut off, which is commonly experienced on online communication platforms. Additionally, the company announced that it has defaulted its machine learning-based noise cancellation technology for Teams (Windows, Mac, and iOS and soon for Teams Android and Web clients), enabling clearer noise-free calls. unwanted.

Microsoft is also extending the use of AI to Teams video performance to create relevant visual adjustments, especially in cases where users experience problematic bandwidth conditions while sharing content during presentations. For example, Teams’ real-time screen optimization feature that uses machine learning can detect and adjust content characteristics, resulting in improved document readability and smooth video playback. Meanwhile, by adjusting the video playback, the AI-based optimization prevents the drastic effects of choppy videos caused by poor network bandwidth. Finally, new AI-powered filters in Teams allow users to adjust brightness and use soft focus when having meetings in low-light areas.

According to Microsoft, said mentioned features are currently being rolled out and will be generally available in the coming months.


Comments are closed.