Git Product home page Git Product logo

koe's Introduction

Koe: open-source software to visualise, segment and classify acoustic units in animal vocalisations

What is it?

Koe is an application for classifying and analysing animal vocalisations. Koe offers bulk-labelling of units via interactive ordination plots, as well as visualisation and playback, segmentation, measurement, data filtering/exporting and new tools for analysing repertoire and sequence structure -- all in an integrated database.

Koe's unit table is designed for classifying, annotating and filtering units. Each unit row contains a spectrogram which becomes enlarged during mouse-over. Unit audio plays when a spectrogram is clicked. The table can be sorted/filtered by any columns. Sorting by the Similarity Index column arranges units by spectral similarity for expedited labelling. Example data are New Zealand bellbird Anthornis melanura song units.

Segment songs into units view, showing a song being segmented into units. The interface for partitioning recordings into songs is similar. Units are manually segmented by dragging over the spectrogram; unit endpoints can be re-adjusted at any time. A selection box can be clicked for playback. Spectrogram zoom, contrast and colourmap can be adjusted. Units can be labelled, or comments given. This example is a female New Zealand bellbird (Anthornis melanura) song from Hauturu.

Koe's interactive ordination view allows the user to encircle groups of points on the plot with the lasso tool, to view their spectrograms and hear their audio. Mousing over a point in a selection highlights the corresponding spectrogram in the left-hand panel. Selections can be labelled in bulk directly on the plot or opened as a unit table to view detailed unit information. The user can zoom, toggle the visibility of classes, and export the plot as a vector graphic. This example shows a t-SNE ordination of 7189 units of male and female New Zealand bellbird Anthornis melanura song on Tiritiri Matangi Island.

How to install, run and deploy this on your own?

I recommend using the official website at https://koe.io.ac.nz. However if you want to run Koe on your own computer/server, here's how:

Install

Run

Upgrade

Deploy

Licence

License: GPL v3

This work is distrbuted under GPL version 3.0 licence.

Read the full LICENCE here

Contact us if you want a different licence option.

Copyright

Copyright (c) 2013-9999 Yukio Fukuzawa. All rights reserved.

koe's People

Contributors

fzyukio avatar agnz avatar jren2019 avatar

Watchers

James Cloos avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.