A Demand-Driven Perspective on Generative Audio AI
This work addresses the gap between AI research and practical deployment in the audio industry, but it is incremental as it primarily surveys existing challenges without introducing new methods.
The paper tackled the problem of aligning generative audio AI research with industry demands by surveying professional audio engineers to identify research priorities and challenges, resulting in findings that dataset availability is the main bottleneck for high-quality audio generation.
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.