What you need to know
- Microsoft is rolling out two new audio features for Teams.
- Machine-learning-based noise suppression is now generally available.
- Automatic music detection is expected to roll out in the coming months.
Microsoft has a couple of new audio features in the works for Teams. Machine-learning-based noise suppression can automatically detect background noise that needs to be suppressed, allowing the communication app to make speech audio clearer within meetings. An automatic music detection feature is also on the way to Teams, though people will have to wait a few months to try it out.
High-fidelity music mode transmits audio signals with a 32kHz sampling rate (16kHz bandwidth) at 128kbps. The mode reduces bitrate by four times compared to lossless encoding. Microsoft built the new feature with music lessons and performances in mind. The company explains that High-fidelity music mode can also clearly transmit medical signals during a virtual appointment.
Microsoft shares audio samples of music in a regular meeting and music in High-fidelity music mode for comparison. The music in the regular meeting sounds a bit empty, and it's clearly been transmitted through the web and compressed. In contrast, the audio from high-fidelity music mode sounds richer.
Microsoft also has news about another audio-related feature, machine-learning-based noise suppression. Most Teams customers should now have the option on by default. It identifies non-speech audio to suppress, making it easier to hear people speaking within a meeting. Teams will automatically detect if non-speech audio is music and then show a prompt to enable High-fidelity music mode.
Over 1 million audio clips were used to train Microsoft's deep neural network. The company had musicians play several instruments across a range of genres to test the feature.
Microsoft Teams is an incredibly popular communication platform, especially among office workers and professionals. New features for the app should help deliver clear audio for speech and music.
