Google introduces AI-powered feature in YouTube Stories

Google introduces AI-powered feature in YouTube Stories. | Picture by special arrangement.  

(Subscribe to our Today's Cache newsletter for a quick snapshot of top 5 tech stories. Click here to subscribe for free.)

Google has introduced an AI-powered feature in YouTube Stories, allowing users to enhance the quality of their selfie videos with altered voice and reduced background noise.

“While tremendous efforts are invested in improving the quality of videos taken with smartphone cameras, the quality of audio in videos is often overlooked,” Google noted in a blog post.


'Enhance speech' feature is based on machine learning (ML) technology, and uses both audio and visual signals to distinguish voices of people in a video from one another and other background noise.

The feature fuses 'enhanced speech' with just 10% background noise to improve video quality in iOS devices. YouTube Stories users can access the feature from volume controls editing tool.

After the video is recorded, the audio and the visual features are processed using the speech separation model to produce the enhanced speech.

Google claims the optimisations and improvements has significantly reduced its processing time, just with the help of a smartphone's CPU. It has also brought down the memory use from 120MB to 6MB, making it easy for use.

The search giant said it had trained the ML model on a large collection of online videos, to capture connections between speech and visual signals such as mouth movements and facial expressions. And tested the technology’s performance in different recording conditions. and on people with different appearances and voices.

This article is closed for comments.
Please Email the Editor

Printable version | Jan 21, 2021 8:53:23 AM |

Next Story