Microsoft wants to revolutionize the dubbing industry with this surprising patent

One of the most interesting tools that have been released recently when it comes to dubbing is Aloud powered by artificial intelligence and available for YouTube, which basically allows you to dub what you are watching and speak it in multiple languages.

Microsoft could be working on something similar, but much better, although at the moment there is nothing tangible, since it has been discovered in a patent.

What Microsoft wants to do is double multimedia content using the user’s own voice and also in their own original language.

Microsoft wants to create a system where voices are extracted from multimedia content and a model of the user’s voice is created.

So when the user chooses a medium to play on the device, the system would use this model to create voices that sound like their own, replacing the original voices of the medium.

It is commented in the patent that this process could also be carried out in other languages, in addition, Options would appear to customize the voices with different tones and even different translations in other languages.

On the other hand, this technology would also eliminate background noises by using different audio channels capable of separating voice and background sound very effectively.

“To provide multiple audio versions for specific multimedia content, voice actors are hired. dubbing to read different versions of scripts. This traditional dubbing process is very expensive and time-consuming,” Microsoft argues to justify the patent.