Evaluating deep learned voice compression for use in video games

• Published in: Expert systems with applications Vol. 181; p. 115180
• Main Authors: Possemiers, Aidan, Lee, Ickjai
• Format: Journal Article
• Language: English
• Published: New York Elsevier Ltd 01.11.2021; Elsevier BV
• Subjects: Acceptable noise levels; Compression tests; Computer & video games; Computer graphics; Criteria; Deep learning; Machine learning; Music; Objective voice quality measurement; Sound effects; Video compression; Video games; Voice; Voice compression; Deep learning; Video games; Objective voice quality measurement; Voice compression; Performance
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2021.115180

•Identification of the key unique characteristics in the game audio compression.•Outline the dataset requirements to adequately test video game quality audio.•Propose and perform objective performance measures on video game audio data.•Provide initial results on off-the-shelf versions of the algorithms.•Evaluate any gaps that need to be addressed. In recent years video games have become one of the most popular entertainment mediums. This can partly be attributed to advances in computer graphics, and the availability, affordability and performance of hardware which have made modern video games the most realistic and immersive they have ever been. These games have a rich story with large open worlds, and a diverse cast of fully voice acted characters which also means that they take up large amounts of disk space. While a large percentage of this audio is sound effects and music, modern, character-driven, open world games contain multiple hours and many gigabytes of spoken voice audio. This paper examines how audio compression in video games poses distinctly different challenges than in telecommunications or archiving, the primary motivating factor that inspired audio compression systems currently used in video games. By evaluating new, deep learning based, methods of voice compression with video games in mind, we determine the criteria needed to be met for a new method to succeed current methods in measures of compression factor and quality at an acceptable level of algorithmic performance and what directions new research is needed to meet this criteria.