A Demand-Driven Perspective on Generative Audio AI

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. The survey was conducted to determine research priorities and define various research tasks. Additionally, we summarize the current challenges in audio quality and controllability, based on the survey results. Our analysis reveals that the availability of datasets is currently the main bottleneck for achieving high-quality audio generation. Lastly, drawing on our experience, we suggest potential solutions and provide supporting empirical evidence.

Cite

Text

Oh et al. "A Demand-Driven Perspective on Generative Audio AI." ICML 2023 Workshops: DeployableGenerativeAI, 2023.

Markdown

[Oh et al. "A Demand-Driven Perspective on Generative Audio AI." ICML 2023 Workshops: DeployableGenerativeAI, 2023.](https://mlanthology.org/icmlw/2023/oh2023icmlw-demanddriven/)

BibTeX

@inproceedings{oh2023icmlw-demanddriven,
  title     = {{A Demand-Driven Perspective on Generative Audio AI}},
  author    = {Oh, Sangshin and Kang, Minsung and Moon, Hyeongi and Choi, Keunwoo and Chon, Ben Sangbae},
  booktitle = {ICML 2023 Workshops: DeployableGenerativeAI},
  year      = {2023},
  url       = {https://mlanthology.org/icmlw/2023/oh2023icmlw-demanddriven/}
}