Popular video and voice calling application Skype has received a slew of updates and features ever since the lockdown phase kicked in last year. The emphasis has been on providing tools that make the user’s voice and video experience better. Now the company has added yet another feather to its hat by introducing an AI-enabled noise cancellation feature to the desktop version of Skype.
In a recent blog post, Skype said that the technology was originally made for Microsoft Teams. “We are pleased to announce the release of our latest background noise suppression feature in the Skype desktop app. Originally developed for Microsoft Teams, this new feature is designed to silence just about everything except for your voice when you’re meeting on Skype,” it adds.
How to activate noise cancellation on Skype
You can activate the feature by:
– Going to the Settings option on the desktop version of the app.
– In Settings, go to the Audio and Video option.
– In Audio and Video, you need to scroll down to the Noise Cancellation option.
– Click on the arrow at the end of the Noise Cancellation tab and select ‘High’.
You should know that the feature is not available in the web version or the mobile version of the app rather has only been made available on the desktop app. The option is also available in the Mac version.
How does the tech work?
The new noise cancellation feature will analyse your audio and used deep neutral networks to remove the noise in the background without affecting the speaker’s voice. This technology is different from conventional noise cancellation tech as the former cannot differentiate when it comes to more complex noises like typing on the keyboard, the crunch of a food wrapper or when your pet dog is howling.
“This technology relies on machine learning (ML) to learn the difference between clean speech and noise and is frequently referred to as artificial intelligence (AI). A representative dataset is used to train the ML model to work in most of the situations our Skype users experience. There needs to be enough diversity in the dataset in terms of the clean speech, noise types, and the environments from which our users are joining online calls,” the post stated.
The company says that it used up to 760 hours of clean speech data and 180 hours of noise data in its training module. Most of the noise data that it collected included sounds in different scenarios including snoring, running water, keyboard typing, etc.