The new patent outlines a system, which you can see visually below, that sees players input speech into a synthesizer that goes through a converter and vocoder to the game.
“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,” the patent’s abstract reads.
“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. The target acoustic features are processed with one or more modules, to generate speech audio in the voice of the player.”
In addition to recording their own voice, this feature would allow text input. This would let players type the dialogue they want their character to say.
What do you think about eventually providing the voices for in-game video game characters yourself if the EA patent becomes a reality? For more Insider Gaming, check out the latest on Undisputed boxing’s career mode and character creator.