EA Patents To Let Players Voice Characters In Video Games

Quite a few games have already tried to use the voice of players as an input, but it is rare and limited in practice. Regardless, EA seems to be exploring that feature for its future titles. A new patent published by the company wants players to become the voice of characters in games. The players’ voices would be used as input and processed into the voice of characters using AI. The system would only rely on minutes of recorded user data.

Systems and methods as described in this specification enable speech audio to be generated in the voice of a player of a video game, using speech audio provided by the player (e.g. a small amount of speech audio such as minutes of speech audio from the player), and a voice convertor.”

The patent dubbed “GENERATING SPEECH IN THE VOICE OF A PLAYER OF A VIDEO GAME,” argues that previous approaches to voice NPCs by using the audio recordings of users have been barred by the limits of technology, like requiring hours of speech samples. It is also worth noting that capturing all the emotions and depth of a player’s voice, even with hours of voice data, was impossible in the past decades.

In some video games, players may be able to configure their avatars to speak in different voices. However, previous approaches of generating speech audio in a particular voice typically require many speech samples (e.g. hours of speech samples) in order for the synthesizer to accurately capture the voice in the synthesized speech audio.”

EA may ask the players to repeat specific phrases in their voice before the playthrough to record the audio. The input voice of the player would then be converted into the speech of the game character, ensuring that speech prosody, such as intonation, stress, rhythm, and style of speech, still feels natural and detailed.

Related Content:

• EA Patents To Let Players Play As A Videographer In-Game To Record Gameplay.
• EA Patents To Potentially Ban Players For Partnering Up With Enemy Team Members.
• EA Patents To Reenact Playable Moments From Recorded Gameplay Videos.

The patent solves the dilemma of not having a player’s personalized voice as speech for in-game characters. The newly proposed system could prove to be a popular feature if the emotions of a game character can be portrayed using the voice input of the players. 

Nevertheless, such a tech is a risky gamble for the gaming industry. The proposed system and its evolution can threaten the standard voice-acting roles if it starts to be used more commonly in games.