Audio clips of people saying a digit are pushed through a denoising autoencoder and then through a CNN to classify the digit being said.
Data was a couple of GB and not included. classifies to 98% accuracy.
-
Notifications
You must be signed in to change notification settings - Fork 0
NotRunningJ/AI-Audio-Classifier
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Audio clips of people saying a digit are pushed through a denoising autoencoder and then through a CNN to classify the digit being said.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published