https://github.com/janclemenslab/das
Deep Audio Segmenter
https://github.com/janclemenslab/das
annotation classification deep-learning segmentation song tensorflow
Last synced: 4 months ago
JSON representation
Deep Audio Segmenter
- Host: GitHub
- URL: https://github.com/janclemenslab/das
- Owner: janclemenslab
- License: apache-2.0
- Created: 2019-09-26T19:11:24.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2025-10-21T10:30:10.000Z (8 months ago)
- Last Synced: 2026-01-13T17:09:55.912Z (5 months ago)
- Topics: annotation, classification, deep-learning, segmentation, song, tensorflow
- Language: Python
- Homepage: http://janclemenslab.org/das/
- Size: 88.1 MB
- Stars: 32
- Watchers: 5
- Forks: 10
- Open Issues: 12
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Deep Audio Segmenter
_DAS_ is a method for automatically annotating song from raw audio recordings based on a deep neural network. _DAS_ can be used with a graphical user interface, from the terminal, or from within python scripts.
If you have questions, feedback, or find bugs please raise an [issue](https://github.com/janclemenslab/das/issues).
Please cite _DAS_ as:
Elsa Steinfath, Adrian Palacios, Julian Rottschäfer, Deniz Yuezak, Jan Clemens (2021).
_Fast and accurate annotation of acoustic signals with deep neural networks._
[eLife](https://doi.org/10.7554/eLife.68837)
See the documentation at [https://janclemenslab.org/das/](https://janclemenslab.org/das/) for instructions on how to [install DAS](https://janclemenslab.org/das/installation.html) and for a user guide:
- A [quick start tutorial](https://janclemenslab.org/das/quickstart.html) walks through all steps from manually annotating song, over training a network, to generating new annotations.
- How to use the [graphical user interface](https://janclemenslab.org/das/tutorials_gui/tutorials_gui.html).
- How to use _DAS_ [from the terminal or from python scripts](https://janclemenslab.org/das/tutorials/tutorials.html).
## Acknowledgements
The following packages were modified and integrated into das:
- Keras implementation of TCN models modified from [keras-tcn](https://github.com/philipperemy/keras-tcn) (in `das.tcn`)
- Trainable STFT layer implementation modified from [kapre](https://github.com/keunwoochoi/kapre) (in `das.kapre`)
See the sub-module directories for the original READMEs.