The authors present Euterpe, a prototyping web framework designed to facilitate the deployment of interactive music systems on the web. Utilizing the web's natural cross-platform compatibility, Euterpe enables widespread accessibility to these systems, potentially maximizing their impact. One of the authors' main goals is to reduce the burden on developers by providing support in handling the JavaScript aspects of implementation. Although developers still need to write JavaScript for their core algorithms, Euterpe assumes the responsibilities of receiving both audio and MIDI real-time input streams, synchronizing them, and sending them to the core algorithm in a structured fashion. Additionally, the authors offer pre-built functionalities for input and output data visualization. To showcase the capabilities of Euterpe, the authors conduct case studies on the deployment of "BachDuet" and "JazzImprov," two neural network music improvisation algorithms that were previously inaccessible to the general public. Through these case studies, valuable feedback is gathered from both end users who interacted with BachDuet and the independent developer who created JazzImprov. Euterpe is open-sourced at https://github.com/yongyizang/Euterpe.

Authors: Zang, Yongyi; Benetatos, Christodoulos; Duan, Zhiyao
Affiliations: Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY; Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY; Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY(See document for exact affiliation information.)
JAES Volume 71 Issue 11 pp. 738-752; November 2023
Publication Date: November 16, 2023 Import into BibTeX
Permalink: https://www.aes.org/e-lib/browse.cfm?elib=22340

Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!

This paper costs $33 for non-members and is free for AES members and E-Library subscribers.

Learn more about the AES E-Library

E-Library Location: (CD JAES71)   /jaes71/11/pg738.pdf

DOI: https://doi.org/10.17743/jaes.2022.0117

Start a discussion about this paper!