You might have noticed a marked improvement in the audio quality of some YouTube Stories going forward, this is all possible because of the new speech enhancements feature Google rolled out. A few years back, the tech giant debuted the “Looking to listen” AI technology that can pick out a voice from the crowd. Now, it’s making the technology available to create recording YouTube Stories on iOS devices.
The company taught looking to listen to the correlations between speech and visual signals, such as the speaker’s mouth movements and facial expressions, by training it on a large collection of online videos. To make sure that it will work for everyone and won’t show bias, Google conducted a series of tests exploring its performance based on various visual and auditory attributes.
Those attributes include the speaker’s age, skin tone, spoken language, voice pitch, visibility of their face, head pose, facial hair, presence of glasses, and the level of background noise. They were able to confirm, for example, that the technology’s capability to enhance speech remains pretty consistent across speaker’s languages.
Google also went on to explain in its announcement post how it has improved the technology over the past couple of years. They also used a technique that allows the feature to extract thumbnails with faces from videos for analysis very quickly. Those improvements shrunk the feature’s size from 120MB to 6MB, making it easier to deploy. Those improvements shrunk the feature’s size from 120MB to 6MB, making it easier to deploy. Those improvements shrunk the feature’s size from 120MB to 6MB, making it easier to deploy. Those improvements shrunk the feature’s size from 120MB to 6MB, making it easier to deploy.
To access this feature, creators only have to toggle to Enhance speech in volume controls on iOS.
TECH NEWS>>>>Google Reveals New Pixels, Chromecast And More
