A Demand-Driven Perspective on Generative Audio AI

TL;DR

This paper surveys professional audio engineers to identify industry demands and research priorities in generative audio AI, highlighting dataset availability as a key bottleneck and proposing potential solutions.

Contribution

It provides a demand-driven analysis of generative audio AI, emphasizing industry needs, challenges, and potential solutions based on survey data.

Findings

Dataset availability is the main bottleneck for high-quality audio generation.

Industry demands prioritize controllability and audio quality.

Proposed solutions are supported by empirical evidence.

Abstract

To achieve successful deployment of AI research, it is crucial to understand the demands of the industry. In this paper, we present the results of a survey conducted with professional audio engineers, in order to determine research priorities and define various research tasks. We also summarize the current challenges in audio quality and controllability based on the survey. Our analysis emphasizes that the availability of datasets is currently the main bottleneck for achieving high-quality audio generation. Finally, we suggest potential solutions for some revealed issues with empirical evidence.