Conditioning Deep Generative Raw Audio Models for Structured Automatic Music.

Rachel Manzelli Vijay Thakkar Ali Siahkamari Brian Kulis

Published in: ISMIR (2018)

Keyphrases

prior knowledge
probabilistic model
music information retrieval
speech music discrimination
audio signals
unsupervised learning
data driven
generative model
multi modal
parameter estimation
semi automatic
statistical models
raw data
computational models
probability distribution
audio recordings
neural network