Improving Neural Net Auto Encoders for Music Synthesis

Colonel J, Curro C, Keene S. Improving Neural Net Auto Encoders for Music Synthesis. In: AES Convention 143. Audio Engineering Society; 2017. Paper 9846. Available from: https://aes.org/publications/elibrary-page/?id=19243

@inproceedings{Colonel2017_19243,
  author = {Colonel, Joseph and Curro, Christopher and Keene, Sam},
  title = {{Improving Neural Net Auto Encoders for Music Synthesis}},
  booktitle = {AES Convention 143},
  note = {Paper 9846},
  year = {2017},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=19243}
}

TY  - CPAPER
TI  - Improving Neural Net Auto Encoders for Music Synthesis
AU  - Colonel, Joseph
AU  - Curro, Christopher
AU  - Keene, Sam
T2  - AES Convention 143
M1  - Paper 9846
PY  - 2017
DA  - 2017/10/06
UR  - https://aes.org/publications/elibrary-page/?id=19243
PB  - Audio Engineering Society
LA  - en
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.
ER  -