A new speech enhancement option within YouTube Stories has been launched this week by Google that will let users reduce background noise in video clips they make, putting more emphasis on the main subject.
According to the Google AI Blog:
“We are now happy to make the Looking to Listen technology available to users through a new audiovisual Speech Enhancement feature in YouTube Stories (on iOS), allowing creators to take better selfie videos by automatically enhancing their voices and reducing background noise.”
The new option will reduce background noise, which will help improve the presentation of the video, and will help clarify speech. This is based on technology developed by Google (which is still ongoing) that utilizes marching learning to isolate the speech of a video’s subject.
Google explained it this way:
“By training the model on a large-scale collection of online videos, we are able to capture correlations between speech and visual signals, such as mouth movements and facial expressions, which can then be used to separate the speech of one person in a video from another, or to separate speech from background sounds. This technology not only achieves state-of-the-art results in speech separation and enhancement (a noticeable 1.5dB improvement over audio-only models), but in particular, can improve the results over audio-only processing when there are multiple people speaking, as the visual cues in the video help determine who is saying what.”