@inproceedings{7ad14de7db954bd58a39377449b6b2a8,
title = "Neural Music Synthesis for Flexible Timbre Control",
abstract = "The recent success of raw audio waveform synthesis models like WaveNet motivates a new approach for music synthesis, in which the entire process - creating audio samples from a score and instrument information - is modeled using generative neural networks. This paper describes a neural music synthesis model with flexible timbre controls, which consists of a recurrent neural network conditioned on a learned instrument embedding followed by a WaveNet vocoder. The learned embedding space successfully captures the diverse variations in timbres within a large dataset and enables timbre control and morphing by interpolating between instruments in the embedding space. The synthesis quality is evaluated both numerically and perceptually, and an interactive web demo is presented.",
keywords = "Music Synthesis, Timbre Embedding, WaveNet",
author = "Kim, {Jong Wook} and Rachel Bittner and Aparna Kumar and Bello, {Juan Pablo}",
note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 ; Conference date: 12-05-2019 Through 17-05-2019",
year = "2019",
month = may,
doi = "10.1109/ICASSP.2019.8683596",
language = "English (US)",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "176--180",
booktitle = "2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings",
}