Skip to content

Home

Jump to bottom
Ciumac Sergiu edited this page Jun 2, 2013 · 25 revisions

Welcome to the Sound Fingerprinting Wiki!

Sound Fingerprinting is an exciting field, thus the aim of this project is to implement an efficient algorithm of signal processing which will allow one to have a competent system of audio fingerprinting and signal recognition. The algorithm which is implemented was developed by Google researchers, and published in Content fingerprinting using wavelets paper.

Explanation of the algorithm alongside with a demo application can be found here.

The implemented algorithm can be used in a variety of different types of applications:

  1. Automatic population the metadata of a song - MusicBrainz
  2. Identifying a currently playing song - Shazam
  3. Monitoring radio broadcasts
  4. Managing sound effect libraries
  5. Speech recognition programs

The source code is still in an experimental phase. Currently, I'm working on compiling a set of developed services to a easy to use assembly.

If you do have any questions and/or propositions related to library structure, feel free to open issues, or contact me directly.

Clone this wiki locally