bbc/clever-thumbnailer

Name: clever-thumbnailer

Owner: BBC

Description: Audio thumbnail generator

Created: 2015-08-04 14:55:20.0

Updated: 2018-05-22 17:21:32.0

Pushed: 2017-01-31 11:54:53.0

Homepage:

Size: 258

Language: C

GitHub Committers

User	Most Recent Commit	# Commits

Other Committers

User	Email	Most Recent Commit	# Commits

README

CleverThumbnailer

Cleverthumbnailer is a command line tool that analyses songs and creates short audio thumbnails of them.

Algorithm

Given a full length piece of music in WAVE format (*.bwf and *.wav), cleverthumbnailer attempts to generate a short extract most representative of the track in general. It bases this decision on three factors:

1. Segment Detection. Using the QMUL Segmenter algorithm, distinct musical sections of a piece are found. In western pop music, this algorithm detects transitions between verses, choruses, and bridges. In western classical music, segment boundaries are often found at key changes/modulations.
2. RMS Energy profiling. The varying dynamics of a piece of music are calculated by tracking the RMS energy over the course of a piece. Sections of a piece that are loud (by default) or have a high amount of dynamic variation (--dynamic flag) are preferred for inclusion in the audio snippet generated.
3. Applause detection. An algorithm that determines spectral centroid over time is used to detect applause within a recording. Periods of applause are avoided in the resulting audio thumbnail.

Installation

Usage

er-thumbnailer version 0.1.0

e: clever-thumbnailer [options] <inputfile> <outputfile>
a             Enable applause detection
c <cropin>    Crop time from start in seconds (default 7.0)
C <cropout>   Crop time from end in seconds (default 7.0)
d             Rate sections by dynamic range rather than max loudness
f <fadein>    Fade-in duration in seconds (default 0.5)
F <fadeout>   Fade-out duration in seconds (default 2.0)
h             Display this help message
l <length>    Thumbnail length in seconds (default 30.0)
p <prelude>   Seconds of additional lead-in (default 10.0)
q             Enable quiet mode
v             Enable verbose mode

Credits

The code in this repository was created by Jon Tutcher in 2015 for BBC Research & Development.

QM-DSP was created by Queen Mary University of London; the segmenter module used here was developed by Mark Levy and Chris Cannam.

License

This project is licensed under the GNU GPLv2 license. For terms and conditions, see LICENSE.