Code Monkey home page Code Monkey logo

bof-aed's Introduction

Bag-of-Features Acoustic Event Classification and Detection with multi-channel fusion

This is Python code for Bag-of-Features representations for acoustic event detection and classification. The method for multi-channel fusion is described in [3] and the single-channel method in [1,2]. It also includes a two demos:

  • Classifying single-channel acoustic events on the FINCA acoustic event dataset
  • Classifying multi-channel events on the FINCA multi-channel dataset

For details please read the 'Getting started' section

Note that this is a updated version of the code used in the publications ([1,2,3]). Some dependencies have been replaced by python libraries that are easier to handle. If you have used one of our previous - non github - release, the results may differ slightly.

References

[1] A Bag-of-Features Approach to Acoustic Event Detection Axel Plinge, Rene Grzeszick, Gernot A. Fink. Int. Conf. on Acoustics, Speech and Signal Processing, 2014.

[2] Temporal Acoustic Words for Online Acoustic Event Detection Rene Grzeszick, Axel Plinge, Gernot A. Fink. German Conf. Pattern Recognition, 2015.

[3] Bag-of-Features Acoustic Event Detection for Sensor Networks Julian Kürby, Rene Grzeszick, Axel Plinge, and Gernot A. Fink. Detection and Classification of Acoustic Scenes and Events (DCASE) Workshop, Budapest, Hungary, 2016.

If you use this code in your scientific work please cite the corresponding paper.

System Requirements

  • Python
  • Numpy
  • Scipy
  • Sklearn
  • pysoundfile

The software was tested on Debian 64bit.

Getting started

  1. Either add the src folder to your PYTHONPATH or use a Python IDE of your liking (e.g. Eclipse and pydev)
  2. Use the multi_channel_experiments or the single_channel_experiment sample file to include our code in your experiments

For running the sample experiments:

  1. Download the FINCA "Multi-channel acoustic event dataset" for multi-channel experiments or the FINCA "Acoustic event dataset" for single-channel experiments from http://patrec.cs.tu-dortmund.de/cms/en/home/Resources/index.html
  2. Set the respective FINCA_DATASET_PATH in the demo file
  3. Run the experiment

Contact Authors

Rene Grzesick Department of Computer Science TU-Dortmund, Germany. Email: [email protected]

Axel Plinge Department of Computer Science TU-Dortmund, Germany. Email: [email protected]

Julian Kürby Department of Computer Science TU-Dortmund, Germany. Email: [email protected]

bof-aed's People

Contributors

rgrzeszi 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.