Google has recently launched a new feature of speech enhancement within YouTube Stories. With this option, users can reduce background noise in their video clips, which will clarify speech of the subject in the video. The tool is actually part of Google’s current work on speech-to-text- translation.
Speech enhancement technology uses machine learning to isolate the speech of a video’s subject.
As explained by Google, the model will be applied on large-scale collection of online videos, which will help capture correlations between speech and video signals, like mouth movements and facial expressions. This will further assist in separating the speech of one subject in a video from another, or distinguishing the subject’s 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.", the tech giant further clarified.
The speech enhancement option can be enabled from the Story upload settings as part of the volume controls editing tool. The to is only available to iOS users for now and only users who are eligible for YouTube stories can access it, as YouTube Stories is only available to channels with over 10,000 subscribers. YouTube is, however, considering making the feature available to a greater audience in the near future.
YouTube is also removing the option of adding music from the Audio Library to YouTube stories, as it has observed minimum usage of the feature.