This week, Google has started a new option for speech enhancement in YouTube Stories. The new feature will help users reduce background noise in their videos and put more focus on the main topic.
As you can see in the video above, users can apply the new option from their upload settings. It will decrease the background noise, improve the key presentation, and will also clarify speech.
Google is foremost working on speech-to-text translation and this option is part of the technology, using machine learning to clarify speech from any noise in a video.
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.”
Obviously, that has the app beyond developing your Stories, yet YouTube Stories offers a good testing ground for the new process. Also, though providing users a new way to enhance their Stories presentation and sound.
If you are a YouTube creator who is eligible for YouTube Stories, and you want to implement the option, you can record the video, then choose “Enhance speech” from the volume editing tool. Only iOS users are able to apply this so far.
YouTube Stories creation is not available to everyone. YouTube Stories is just available for creators who have more than 10k subscribers. However, the platform is planning to open up the feature fore more users soon.
Excitingly, YouTube will stop creators from adding music from the Audio Library to the Stories soon. It seems to be a step back, but the platform stated that the feature has very low usage.
However, regardless of the availability, it is an interesting feature that will also get more interesting when you see whether Google is planning to make a noise reduction tool accessible for more users anytime soon.