An open-source Python library and command-line tool for classifying bird species from flight calls in audio recordings.
BirdVoxClassify is a pre-trained deep learning system for classifying bird species from flight calls in short audio recordings. It relies on per-channel energy normalization (PCEN) for improved robustness to background noise. It is made available both as a Python library and as a command-line tool for Windows, OS X, and Linux.
The code used to train these models can be found at this repository.
Currently, we support Python 3.6, 3.7, and 3.8.
BirdVoxClassify depends on the SoundFile module to load audio files, which itself depends on the non-Python library libsndfile.
On Windows and Mac OS X, these will be installed automatically via the pip package manager and you can therefore skip this step.
However, on Linux, libsndfile must be installed manually via your platform's package manager.
For Debian-based distributions (such as Ubuntu), this can be done by simply running
apt-get install libsndfile
For more detailed information, please consult the installation instructions of soundfile.
We have dropped support for Tensorflow 1.x, and have moved to Tensorflow 2.x.
The simplest way to install BirdVoxClassify is by using pip, which will also install the additional required dependencies
if needed.
To install the latest version of BirdVoxClassify from source:
-
Clone or pull the latest version:
git clone [email protected]:BirdVox/birdvoxclassify.git -
Install using pip to handle Python dependencies:
cd birdvoxclassify pip install -e .
Aurora Cramer, New York University (@auroracramer on GitHub).
For more information on the BirdVox project, please visit our website: https://wp.nyu.edu/birdvox
See the BirdVox Google Group for questions and relevant discussion regarding BirdVox research and tools.
Please cite the following paper when using BirdVoxClassify in your work:
Chirping up the Right Tree: Incorporating Biological Taxonomies into Deep Bioacoustic Classifiers
Jason Cramer, Vincent Lostanlen, Andrew Farnsworth, Justin Salamon, and Juan Pablo Bello
In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Barcelona, Spain, May 2020.