Improving Neural Net Auto Encoders for Music Synthesis
×
Cite This
Citation & Abstract
J. Colonel, C. Curro, and S. Keene, "Improving Neural Net Auto Encoders for Music Synthesis," Paper 9846, (2017 October.). doi:
J. Colonel, C. Curro, and S. Keene, "Improving Neural Net Auto Encoders for Music Synthesis," Paper 9846, (2017 October.). doi:
Abstract: We present a novel architecture for a synthesizer based on an autoencoder that compresses and reconstructs magnitude short time Fourier transform frames. This architecture outperforms previous topologies by using improved regularization, employing several activation functions, creating a focused training corpus, and implementing the Adam learning method. By multiplying gains to the hidden layer, users can alter the autoencoder’s output, which opens up a palette of sounds unavailable to additive/subtractive synthesizers. Furthermore, our architecture can be quickly re-trained on any sound domain, making it flexible for music synthesis applications. Samples of the autoencoder’s outputs can be found at http://soundcloud.com/ann_synth , and the code used to generate and train the autoencoder is open source, hosted at http://github.com/JTColonel/ann_synth.
@article{colonel2017improving,
author={colonel, joseph and curro, christopher and keene, sam},
journal={journal of the audio engineering society},
title={improving neural net auto encoders for music synthesis},
year={2017},
volume={},
number={},
pages={},
doi={},
month={october},}
@article{colonel2017improving,
author={colonel, joseph and curro, christopher and keene, sam},
journal={journal of the audio engineering society},
title={improving neural net auto encoders for music synthesis},
year={2017},
volume={},
number={},
pages={},
doi={},
month={october},
abstract={we present a novel architecture for a synthesizer based on an autoencoder that compresses and reconstructs magnitude short time fourier transform frames. this architecture outperforms previous topologies by using improved regularization, employing several activation functions, creating a focused training corpus, and implementing the adam learning method. by multiplying gains to the hidden layer, users can alter the autoencoder’s output, which opens up a palette of sounds unavailable to additive/subtractive synthesizers. furthermore, our architecture can be quickly re-trained on any sound domain, making it flexible for music synthesis applications. samples of the autoencoder’s outputs can be found at http://soundcloud.com/ann_synth , and the code used to generate and train the autoencoder is open source, hosted at http://github.com/jtcolonel/ann_synth.},}
TY - paper
TI - Improving Neural Net Auto Encoders for Music Synthesis
SP -
EP -
AU - Colonel, Joseph
AU - Curro, Christopher
AU - Keene, Sam
PY - 2017
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - October 2017
TY - paper
TI - Improving Neural Net Auto Encoders for Music Synthesis
SP -
EP -
AU - Colonel, Joseph
AU - Curro, Christopher
AU - Keene, Sam
PY - 2017
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - October 2017
AB - We present a novel architecture for a synthesizer based on an autoencoder that compresses and reconstructs magnitude short time Fourier transform frames. This architecture outperforms previous topologies by using improved regularization, employing several activation functions, creating a focused training corpus, and implementing the Adam learning method. By multiplying gains to the hidden layer, users can alter the autoencoder’s output, which opens up a palette of sounds unavailable to additive/subtractive synthesizers. Furthermore, our architecture can be quickly re-trained on any sound domain, making it flexible for music synthesis applications. Samples of the autoencoder’s outputs can be found at http://soundcloud.com/ann_synth , and the code used to generate and train the autoencoder is open source, hosted at http://github.com/JTColonel/ann_synth.
We present a novel architecture for a synthesizer based on an autoencoder that compresses and reconstructs magnitude short time Fourier transform frames. This architecture outperforms previous topologies by using improved regularization, employing several activation functions, creating a focused training corpus, and implementing the Adam learning method. By multiplying gains to the hidden layer, users can alter the autoencoder’s output, which opens up a palette of sounds unavailable to additive/subtractive synthesizers. Furthermore, our architecture can be quickly re-trained on any sound domain, making it flexible for music synthesis applications. Samples of the autoencoder’s outputs can be found at http://soundcloud.com/ann_synth , and the code used to generate and train the autoencoder is open source, hosted at http://github.com/JTColonel/ann_synth.
Open Access
Authors:
Colonel, Joseph; Curro, Christopher; Keene, Sam
Affiliation:
The Cooper Union for the Advancement of Science and Art, New York, NY, USA
AES Convention:
143 (October 2017)
Paper Number:
9846
Publication Date:
October 8, 2017Import into BibTeX
Subject:
Signal Processing
Permalink:
http://www.aes.org/e-lib/browse.cfm?elib=19243