Skip to article frontmatterSkip to article content
Site not loading correctly?

This may be due to an incorrect BASE_URL configuration. See the MyST Documentation for reference.

Jupyter Bioacoustic

JupyterLab tools for annotating and reviewing bioacoustic data

Authors
Affiliations
The Eric and Wendy Schmidt Center for Data Science & Environment
University of California, Berkeley
The Eric and Wendy Schmidt Center for Data Science & Environment
University of California, Berkeley
The Eric and Wendy Schmidt Center for Data Science & Environment
University of California, Berkeley

Abstract

Browse a table of audio clips, play each one with a spectrogram, and optionally record verification decisions or annotations — all without leaving the notebook.

Keywords:bioacoustic monitoringjupyterlabspectrogramannotation

Code Repository: https://github.com/SchmidtDSE/jupyter_bioacoustic
API Documentation: https://github.com/SchmidtDSE/jupyter_bioacoustic/wiki
Demo: https://github.com/SchmidtDSE/jupyter_bioacoustic-demo

Introduction

Bioacoustic monitoring allows scientists to track species presence, population dynamics, and migration patterns. Hundreds of monitoring stations across California alone produce over 100 TB[TODO: WHAT IS A GOOD NUMBER HERE] of audio data annually.

AI models such as BirdNET, Perch, and PNW-Owl can process large volumes of this data — but they require annotated training data, and their outputs need human validation.

BioacousticAnnotator is a flexible, easy to configure JupyterLab extension for annotating and reviewing bioacoustic data directly within a notebook. It handles the full annotation-validation loop without leaving the computational environment where the data-processing, model training, and analysis live.

from jupyter_bioacoustic import BioacousticAnnotator

BioacousticAnnotator(data='detections.csv', audio='recording.flac').open()

Why JupyterLab? A typical bioacoustic workflow includes data annotation, model training, validation, production runs, and reporting. Most of these steps happen in Python, often in JupyterLab, but annotation and validation are usually handled with external tools. BioacousticAnnotator brings these steps into the same environment, making the process simpler and more reproducible.

Features

Table of Contents

Jupyter Bioacoustic
Overview