Skip to content

Latest commit

 

History

History
 
 

audioset

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 
 
 

TensorFlow Requirement: 1.x TensorFlow 2 Not Supported

Models for AudioSet: A Large Scale Dataset of Audio Events

This repository provides models and supporting code associated with AudioSet, a dataset of over 2 million human-labeled 10-second YouTube video soundtracks, with labels taken from an ontology of more than 600 audio event classes.

AudioSet was released in March 2017 by Google's Sound Understanding team to provide a common large-scale evaluation task for audio event detection as well as a starting point for a comprehensive vocabulary of sound events.

For more details about AudioSet and the various models we have trained, please visit the AudioSet website and read our papers:

If you use any of our pre-trained models in your published research, we ask that you cite CNN Architectures for Large-Scale Audio Classification. If you use the AudioSet dataset or the released embeddings of AudioSet segments, please cite AudioSet: An ontology and human-labelled dataset for audio events.

Contact

For general questions about AudioSet and these models, please use the [email protected] mailing list.

For technical problems with the released model and code, please open an issue on the tensorflow/models issue tracker and assign to @plakal and @dpwe. Please note that because the issue tracker is shared across all models released by Google, we won't be notified about an issue unless you explicitly @-mention us (@plakal and @dpwe) or assign the issue to us.

Credits

Original authors and reviewers of the code in this package include (in alphabetical order):

  • DAn Ellis
  • Shawn Hershey
  • Aren Jansen
  • Manoj Plakal