Conditioning Autoencoder Latent Spaces for Real-Time Timbre Interpolation and Synthesis

January 30, 2020 Β· Declared Dead Β· πŸ› IEEE International Joint Conference on Neural Network

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Joseph T Colonel, Sam Keene arXiv ID 2001.11296 Category eess.AS: Audio & Speech Cross-listed cs.NE, cs.SD Citations 7 Venue IEEE International Joint Conference on Neural Network Last Checked 3 months ago
Abstract
We compare standard autoencoder topologies' performances for timbre generation. We demonstrate how different activation functions used in the autoencoder's bottleneck distributes a training corpus's embedding. We show that the choice of sigmoid activation in the bottleneck produces a more bounded and uniformly distributed embedding than a leaky rectified linear unit activation. We propose a one-hot encoded chroma feature vector for use in both input augmentation and latent space conditioning. We measure the performance of these networks, and characterize the latent embeddings that arise from the use of this chroma conditioning vector. An open source, real-time timbre synthesis algorithm in Python is outlined and shared.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Audio & Speech

Died the same way β€” πŸ‘» Ghosted