当前位置: X-MOL 学术Leonardo › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
How Music AI Is Useful: Engagements with Composers, Performers and Audiences
Leonardo ( IF 0.3 ) Pub Date : 2021-10-14 , DOI: 10.1162/leon_a_01959
Oded Ben-Tal 1 , Matthew Tobias Harris 2 , Bob L. Sturm 3
Affiliation  

Critical but often overlooked research questions in artificial intelligence applied to music involve the impact of the results for music. How and to what extent does such research contribute to the domain of music? How are the resulting models useful for music practitioners? This article describes work arising from research engaging with composers, musicians and audiences to address such questions: two websites that make their AI models accessible to a wide audience and a professionally recorded album released to expert reviewers to gauge the plausibility of AI-generated material. The authors describe the use of their models as tools for cocreation. Evaluating AI research and music models in such ways illuminates their impact on music-making.



中文翻译:

音乐人工智能的用途:与作曲家、表演者和观众的互动

应用于音乐的人工智能中关键但经常被忽视的研究问题涉及结果对音乐的影响。这种研究如何以及在多大程度上对音乐领域做出了贡献?由此产生的模型对音乐从业者有何用处?本文描述了与作曲家、音乐家和观众合作的研究工作,以解决这些问题:两个网站,让广大观众可以访问他们的 AI 模型,以及向专家审阅者发布的专业录制专辑,以评估 AI 生成材料的合理性。作者描述了使用他们的模型作为共同创造的工具。以这种方式评估人工智能研究和音乐模型可以阐明它们对音乐制作的影响。

更新日期:2021-10-26
down
wechat
bug