OpenSoundscapeΒΆ
OpenSoundscape is free and open source software for the analysis of bioacoustic recordings (GitHub). Its main goals are to allow users to train their own custom species classification models using a variety of frameworks (including convolutional neural networks) and to use trained models to predict whether species are present in field recordings. OpSo can be installed and run on a single computer or in a cluster or cloud environment.
OpenSoundcape is developed and maintained by the Kitzes Lab at the University of Pittsburgh.
The Installation section below provides guidance on installing OpSo. The Tutorials pages below are written as Jupyter Notebooks that can also be downloaded from the project repository on GitHub.
- Audio and spectrograms
- Manipulating audio annotations
- download example files
- View a subset of annotations
- saving annotations to Raven-compatible file
- 1. Split Audio object, then split annotations to match
- 2. Split annotations into labels (without audio splitting)
- 3. Split annotations directly using splitting parameters
- find all the Raven and audio files, and see if they match up one-to-one
- split and save the audio and annotations
- sanity check: look at spectrograms of clips labeled 0 and 1
- Prediction with pre-trained CNNs
- Beginner friendly training and prediction with CNNs
- Preprocessing audio samples with OpenSoundscape
- Preparing audio data
- Intro to Preprocessors
- Initialize a Dataset
- Loading many fixed-duration samples from longer audio files
- Pipelines and actions
- Modifying Actions
- Modifying the pipeline
- Customizing preprocessing to achieve better machine learning outcomes
- Creating a new Preprocessor class
- Defining new Actions
- Advanced CNN training
- RIBBIT Pulse Rate model demonstration