Synthesizing Game Audio Using Deep Neural Networks

Peter Corcoran

doi:http://hdl.handle.net/10379/16684

Synthesizing Game Audio Using Deep Neural Networks

Peter Corcoran

Electrical & Electronic Engineering

Research output: Chapter in Book or Conference Publication/Proceeding › Conference Publication › peer-review

Abstract

High quality audio plays an important role in gaming, contributing to player immersion during gameplay. Creating audio content which matches overall theme and aesthetic is essential, such that players can become fully engrossed in a game environment. Sound effects must also fit well with visual elements of a game so as not to break player immersion. Producing suitable, unique sound effects requires the use of a wide range of audio processing techniques. In this paper, we examine a method of generating in-game audio using Generative Adversarial Networks, and compare this to traditional methods of synthesizing and augmenting audio.

Original language	English (Ireland)
Title of host publication	2018 IEEE GAMES, ENTERTAINMENT, MEDIA CONFERENCE (GEM)
Publisher	IEEE
Number of pages	3
DOIs	https://doi.org/http://hdl.handle.net/10379/16684
Publication status	Published - 1 Jan 2018

Authors (Note for portal: view the doc link for the full list of authors)

Authors
McDonagh, A;Lemley, J;Cassidy, R;Corcoran, P

Access to Document

http://hdl.handle.net/10379/16684

Cite this

@inproceedings{714e2da13d714d49945a5bc73ab99ad0,

title = "Synthesizing Game Audio Using Deep Neural Networks",

abstract = "High quality audio plays an important role in gaming, contributing to player immersion during gameplay. Creating audio content which matches overall theme and aesthetic is essential, such that players can become fully engrossed in a game environment. Sound effects must also fit well with visual elements of a game so as not to break player immersion. Producing suitable, unique sound effects requires the use of a wide range of audio processing techniques. In this paper, we examine a method of generating in-game audio using Generative Adversarial Networks, and compare this to traditional methods of synthesizing and augmenting audio.",

author = "Peter Corcoran",

year = "2018",

month = jan,

day = "1",

doi = "http://hdl.handle.net/10379/16684",

language = "English (Ireland)",

booktitle = "2018 IEEE GAMES, ENTERTAINMENT, MEDIA CONFERENCE (GEM)",

publisher = "IEEE",

}

TY - GEN

T1 - Synthesizing Game Audio Using Deep Neural Networks

AU - Corcoran, Peter

PY - 2018/1/1

Y1 - 2018/1/1

N2 - High quality audio plays an important role in gaming, contributing to player immersion during gameplay. Creating audio content which matches overall theme and aesthetic is essential, such that players can become fully engrossed in a game environment. Sound effects must also fit well with visual elements of a game so as not to break player immersion. Producing suitable, unique sound effects requires the use of a wide range of audio processing techniques. In this paper, we examine a method of generating in-game audio using Generative Adversarial Networks, and compare this to traditional methods of synthesizing and augmenting audio.

AB - High quality audio plays an important role in gaming, contributing to player immersion during gameplay. Creating audio content which matches overall theme and aesthetic is essential, such that players can become fully engrossed in a game environment. Sound effects must also fit well with visual elements of a game so as not to break player immersion. Producing suitable, unique sound effects requires the use of a wide range of audio processing techniques. In this paper, we examine a method of generating in-game audio using Generative Adversarial Networks, and compare this to traditional methods of synthesizing and augmenting audio.

U2 - http://hdl.handle.net/10379/16684

DO - http://hdl.handle.net/10379/16684

M3 - Conference Publication

BT - 2018 IEEE GAMES, ENTERTAINMENT, MEDIA CONFERENCE (GEM)

PB - IEEE

ER -

Synthesizing Game Audio Using Deep Neural Networks

Abstract

Authors (Note for portal: view the doc link for the full list of authors)

Access to Document

Fingerprint

Cite this