Electronic Arts is seemingly working on new technology that allows players to input their voice into the game, which is then replicated/adopted by the in-game character.
The patent was discovered by VeryAliGaming and was originally filed back in October 2020, but only became public earlier this month. The patent reveals a rough outline for a new type of technology that's specifically designed to reproduce the speech of a player within a game through a system that includes a synthesizer module, a voice converter module, and a Vocoder module.
According to the patent, the technology is able to generate speech audio in the player's voice, while also capturing elements such as tone, emotions, and emphasis on specific words. It's interesting to consider playing a game such as Cyberpunk 2077, The Witcher 3, or perhaps a more plain RPG, with the main in-game character sounding exactly like you.
"A computer-implemented method of generating speech audio in a video game is provided. The method includes inputting, into a synthesizer module, input data that represents speech content. Source acoustic features for the speech content in the voice of a source speaker are generated and are input, along with a speaker embedding associated with a player of the video game into an acoustic feature encoder of a voice convertor.
"One or more acoustic feature encodings are generated as output of the acoustic feature encoder, which are inputted into an acoustic feature decoder of the voice convertor to generate target acoustic features. The target acoustic features are processed with one or more modules, to generate speech audio in the voice of the player," reads the patent's abstract.