Electronic Arts Inc.

Jervis Pinto

Navid Aghdaie

Mohsen Sardari

Kilol Gupta

Zahra Shakeri

Harold Henry Chaput

Kazi Zaman

Dhaval Shah

Kazi Atif-Uz Zaman

John Kolen

Kenneth Alan Moss

Siddharth Gururani

Polina Igorevna Gouskova

Farah Mariam Ali

Chetan Nagaraja Rao

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.

Generating speech in the voice of a player of a video game

This specification describes a computer-implemented method of generating speech audio for use in a video game, wherein the speech audio is generated using a voice convertor that has been trained to convert audio data for a source speaker into audio data for a target speaker. The method comprises receiving: (i) source speech audio, and (ii) a target speaker identifier. The source speech audio comprises speech content in the voice of a source speaker. Source acoustic features are determined for the source speech audio. A target speaker embedding associated with the target speaker identifier is generated as output of a speaker encoder of the voice convertor. The target speaker embedding and the source acoustic features are inputted into an acoustic feature encoder of the voice convertor. One or more acoustic feature encodings are generated as output of the acoustic feature encoder. The one or more acoustic feature encodings are derived from the target speaker embedding and the source acoustic features. Target speech audio is generated for the target speaker. The target speech audio comprises the speech content in the voice of the target speaker. The generating comprises decoding the one or more acoustic feature encodings using an acoustic feature decoder of the voice convertor.

Speaker conversion for video games

A system for use in video game development to generate expressive speech audio comprises a user interface configured to receive user-input text data and a user selection of a speech style. The system includes a machine-learned synthesizer comprising a text encoder, a speech style encoder and a decoder. The machine-learned synthesizer is configured to generate one or more text encodings derived from the user-input text data, using the text encoder of the machine-learned synthesizer; generate a speech style encoding by processing a set of speech style features associated with the selected speech style using the speech style encoder of the machine-learned synthesizer; combine the one or more text encodings and the speech style encoding to generate one or more combined encodings; and decode the one or more combined encodings with the decoder of the machine-learned synthesizer to generate predicted acoustic features. The system includes one or more modules configured to process the predicted acoustic features, the one or more modules comprising a machine-learned vocoder configured to generate a waveform of the expressive speech audio.

Generating expressive speech audio from text data

Using user-specific prediction models, it is possible to present an individualized view of messages generated by users playing a shared instance of a video game. Further, users with different subjective views of what is offensive may be presented with different forms or annotations of a message. By personalizing the views of messages generated by users, it is possible to reduce or eliminate the toxic environment that sometimes forms when players, who may be strangers to each other and may be located in disparate locations play a shared instance of a video game. Further, the user-specific prediction models may be adapted to filter or otherwise annotate other undesirable messages that may not be offensive, such as a message generated by one user in a video game that includes a solution to an in-game puzzle that another user may not desire to read as it may spoil the challenge for the user.

Example chat message toxicity assessment process

Growing community of inventors

Foster City, CA, United States of America

Jervis Pinto