This paper presents a non-backend web architecture for generative audio mixing from the Freesound website using a Variational Autoencoder. It is designed to experiment with the nonexisting audios in large audio databases without the need to populate them. It works directly from the browser using JavaScript tools with a serverless approach and relies exclusively on the computational capacity of the client. The platform's Graphical User Interface allows rapid sampling of the autoencoder sound space and is under active development while the logic is finalized. A Variational Autoencoder has been trained to serve as the default model. Users can upload their own to operate independently. The platform aims to provide users with a straightforward and quick-access interface to generative sounds, supporting the audiovisual industry by filling the existing gaps in audio repositories with synthetic media.

Authors: Cámara, Mateo; Blanco, José Luis
Affiliations: Grupo de Aplicaciones del Procesado de Señales, Information Processing and Telecommunication Center; Escuela Técnica Superior de Ingenieros de Telecomunicación, Universidad Politécnica de Madrid, Spain(See document for exact affiliation information.)
JAES Volume 70 Issue 11 pp. 979-989; November 2022
Publication Date: November 15, 2022 Import into BibTeX
Permalink: https://www.aes.org/e-lib/browse.cfm?elib=22021

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 JAES70)   /jaes70/11/pg979.pdf

DOI: https://doi.org/10.17743/jaes.2022.0046

Start a discussion about this paper!