Fast Deep Learning tools for experimental electronic music
Latent Timbre Synthesis is a new audio synthesis method using deep learning
The visualizations below illustrate a latent space generated by a Variational Autoencoder. On the right, the green and red dots represent latent vectors of audio frames of two audio examples from the dataset, while the green is the latent vectors of a synthesized sound generated by interpolating the latent vectors of two original audio files.
https://github.com/ktatar/latent-timbre-synthesis
💿️ Nine composers joined our qualitative study and composed short pieces using Latent Timbre Synthesis. The album is available here: https://medienarchiv.zhdk.ch/entries/376e81a2-a6b9-4b74-91a3-9144c192f8e1
This work has been supported by the Swiss National Science Foundation, the Natural Sciences and Engineering Research Council of Canada, and Social Sciences and Humanities Research Council of Canada.
Ce travail est supporté par le Fonds national Suisse de la recherche scientifique, le Conseil national des sciences et de l’ingénieurie du Canada, et le Conseil national des sciences humaines et sociales du Canada.