Sounderfeit
Cloning a Physical Model Using a Conditional Adversarial Autoencoder
Bibliographic Data
| ID | 5906347 |
|---|---|
| Authors | Stephen Sinclair (0000-0001-7869-3503, Inria Chile, corresponding author) |
| Year | 2018 |
| Volume | 18 |
| Issue | 1 |
| Pages | 44-60 |
| Publication date | 2018-06-19 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Música Hodie (JOURNAL) |
| Journal identifiers | ISSN: 1676-3939 • E-ISSN: 2317-6776 |
| Publisher | Universidade Federal de Goias (PUBLISHER • BR) |
| DOI | 10.5216/mh.v18i1.53570 |
| OpenAlex | W2789037305 |
| Language | EN |
| Citations received | 1 |
| References cited | 3 |
An adversarial autoencoder conditioned on known parameters of a physical modeling bowed string syn- thesizer is evaluated for use in parameter estimation and resynthesis tasks. Latent dimensions are provided to cap- ture variance not explained by the conditional parameters. Results are compared with and without the adversarial training, and a system capable of "copying" a given parameter-signal bidirectional relationship is examined. A real- -time synthesis system built on a generative, conditioned and regularized neural network is presented, allowing to construct engaging sound synthesizers based purely on recorded data
Adversarial system · Artificial neural network · Autoencoder · Generative Adversarial Networks and Image Synthesis · Model Reduction and Neural Networks · Music Technology and Sound Studies
| Citations per year | 0.13 |
|---|---|
| Citation span | 2018 - 2018 (1) |
| Highly cited | No |