Two notebooks that can be used to generate vocalization spectrograms. CVAE_128 is a convolutional variational autoenocder and vaegan128 is a variational autoencoder generative-adversarial network, which also contains some code for griffin-lim inversion of the spectrograms to create audio files. This work has greatly been influenced by Jack Goffinet (https://github.com/jackgoffinet/autoencoded-vocal-analysis) and Tim Sainburg (https://github.com/timsainb/AVGN).
-
Notifications
You must be signed in to change notification settings - Fork 0
ssterrett/vocal_networks
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Analysis and modeling of vocalization using neural networks
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published