Welcome to DAS¶
DAS — short for deep audio segmenter — is a tool for annotating song in audio recordings. At the core of DAS is a deep neural network, implemented in Tensorflow. The network takes single- and multi-channel audio as an input and returns the probability of finding a particular song type for each audio sample. DAS can be used with a graphical user interface for loading audio data, annotating song manually, training a network, and generating annotations on audio. Alternatively, DAS can be used programmatically from the command line, in python notebooks, or in your own python code via the
If you use DAS, please cite:
Elsa Steinfath, Adrian Palacios, Julian Rottschäfer, Deniz Yuezak, Jan Clemens (2021). Fast and accurate annotation of acoustic signals with deep neural networks, bioRxiv, https://doi.org/10.1101/2021.03.26.436927
Convert your own data, train and evaluate a network, predict on new samples in realtime.