In the beginning of October, Google launches new speech enhancement tool, a new option for speech enhancement within YouTube Stories. It enabled users to reduce background noise in their video clips and put a lot more emphasis on the main subject.
The new option can be applied by users in their upload settings which helps reduce background sound, helps improve the main presentation and clarifies speech to a considerable extent. The technology is part of Google’s ongoing work on speech-to-translation (and transliteration) by utilizing machine learning technology in isolating speech of any video’s subject (speech enhancement).
What does Google have to say about this?
According to Google:
“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.”
This obviously has applications beyond improving a normal user’s YouTube Stories clips. But for this process, YouTube stories has a good testing ground to offer whilst also giving users another way to improve their stories presentation (Google launches speech enhancement).
Users who want to apply the new option must first see if they are eligible for YouTube Stories or not. In short, YouTube creators who are eligible to use the YouTube Stories feature can record a video, and then select the ‘enhance speech’ option from volume controls editing tool (at the moment, only iOS supports this feature).
Well, access to YouTube Stories is not granted to everyone as of now as it is available only channels having 10,000 subscribers or more. Though the platform is looking to open it up to more users sometime soon.
In an interesting fashion, YouTube will also stop YouTube Stories creators from adding music from the Audio Library to their stories’ clips. This may seem like YouTube taking a step behind but according to the platform, such an option does not have a high rate of usage.
Regardless of its availability, this option is quite interesting. Whether Google looks to make its background audio reduction tools available in more platforms in the future or not, this development is also interesting and worth noting.