ASAudio: A Survey of Advanced Spatial Audio Research

TL;DR

This survey comprehensively reviews recent advances in spatial audio technologies, categorizing research methods, datasets, and evaluation metrics to provide a systematic overview of the field's progress and challenges.

Contribution

It offers the first systematic categorization and analysis of spatial audio research, including datasets, evaluation metrics, and technological trends, filling a gap in comprehensive literature reviews.

Findings

Categorized spatial audio research by input-output representations and tasks

Summarized datasets and evaluation benchmarks used in the field

Identified key trends and future directions in spatial audio research

Abstract

With the rapid development of spatial audio technologies today, applications in AR, VR, and other scenarios have garnered extensive attention. Unlike traditional mono sound, spatial audio offers a more realistic and immersive auditory experience. Despite notable progress in the field, there remains a lack of comprehensive surveys that systematically organize and analyze these methods and their underlying technologies. In this paper, we provide a comprehensive overview of spatial audio and systematically review recent literature in the area. To address this, we chronologically outlining existing work related to spatial audio and categorize these studies based on input-output representations, as well as generation and understanding tasks, thereby summarizing various research aspects of spatial audio. In addition, we review related datasets, evaluation metrics, and benchmarks, offering insights from both training and evaluation perspectives. Related materials are available at https://github.com/dieKarotte/ASAudio.