“Disruptive echo effects, poor room acoustics, and choppy video are some common issues that hinder the effectiveness of online calls and meetings. Through AI and machine learning, which have become fundamental to our strategy for continual improvement, we’ve identified and are now delivering innovative enhancements in Microsoft Teams that improve such audio and video challenges in ways that are both user-friendly and scalable across environments.” Echo cancellation is especially interesting and something Microsoft Teams users have requested for some time. In a blog on June 13, Microsoft explains how echo cancellations is important to shut down background noise. Microsoft Teams will use machine learning AI models to recognize differences in speaker sound and user voice. The goal is to reduce the number of errors when a participant has their microphone too close to their speakers. Users report in these situations background noise is common because of a sound loop caused by the mic and speakers.
Machine Learning
Moreover, Microsoft’s machine learning model will also be able to convert audio signals into sound. This will mean less echo and sounding like a user in a case. To achieve accuracy with the model, Microsoft tested the AI for 30,000 hours of speech samples to reduce interruptions during normal conversations. According to the company, no customer data was used in the dataset that was used to train its AI models. “Instead, we either used publicly available data or crowdsourcing to collect specific scenarios. We also ensured that we had a balance of female and male speech, as well as 74 different languages,” Microsoft says. Tip of the day: Headsets are a vital tool for communication and can cause stressful moments when they don´t work as planned. In our tutorial we are showing you how to properly set up a headset on your Windows PC so this will be a thing of the past.
