"Teams update: Improve video and audio experiences with AI and machine learning"

On June 13, Microsoft released many new features for its communications platform Teams, focusing on improving voice and video quality. In particular, these new Teams features include echo cancellation, “dereverberation,” background noise suppression, “interruptibility” functionality, real-time screen optimization, AI-based optimization, and brightness and focus filters.

Microsoft Teams Vice President Nicole Herskowitz said of the main issues driving the development of new Teams features: “Destructive echo effects, poor room acoustics and choppy video are barriers to online calling and meeting productivity. "Through artificial intelligence and machine learning, which have become the foundation of our continuous improvement strategy, we have identified and are delivering innovative enhancements in Microsoft Teams to improve this type of functionality in a way that is user-friendly and scalable across environments." Audio and video challenges.”

Teams’ new echo cancellation feature isn’t the only one focused on the echo issues users experience when communicating within the platform. Some of the audio features introduced by Microsoft also target other echo-related issues caused by the environment and audio devices. For example, the new dereverberation feature leverages machine learning models to convert captured audio signals into sounds, preventing sounds from becoming reverberant or making the user sound like they are speaking in a cave.

Another feature also solves echo-related issues caused by audio devices in close proximity to each other. “A natural element of conversation is the ability to interrupt for clarification or verification,” Herskowitz said. “This is accomplished through full-duplex (two-way) audio transmission, allowing users to speak and hear the other person simultaneously. This is achieved without using headphones. When using a device with speakers and microphones in close proximity, it can be difficult to cancel echo while maintaining full-duplex audio. Microsoft Teams uses a model "trained" on 30,000 hours of speech samples to preserve the desired sound while suppressing Unwanted audio signals, resulting in smoother conversations."

Herskowitz said that with Teams' new interruptible capabilities, users can communicate smoothly without the interruptions or interruptions that are common on online communication platforms. Interrupt. Additionally, the company announced that its machine learning-based noise suppression technology will be available by default in Teams (Windows, Mac, and iOS, and soon in the Teams Android and web clients), making calls clearer and free of unnecessary noise Influence.

Microsoft is also extending the use of AI to Teams’ video performance to create relevant visual adjustments, especially if users experience bandwidth issues while sharing content during presentations. For example, Teams’ real-time screen optimization feature uses machine learning to detect and adjust content characteristics to optimize document legibility and smooth video playback. At the same time, by adjusting video playback, AI-based optimization can prevent the drastic impact of video stuttering caused by poor network bandwidth. Finally, new AI filters in Teams allow users to adjust brightness and use soft focus when meeting in low-light areas.

The above is the detailed content of "Teams update: Improve video and audio experiences with AI and machine learning". For more information, please follow other related articles on the PHP Chinese website!