2 aubioonset - a command line tool to extract musical onset times
7 aubioonset [[-i] source] [-o sink]
8 [-r rate] [-B win] [-H hop]
15 aubioonset attempts to detect onset times, the beginning of discrete sound
16 events, in audio signals.
18 When started with an input source (-i/--input), the detected onset times are
19 given on the console, in seconds.
21 When started without an input source, or with the jack option (-j/--jack),
22 aubioonset starts in jack mode.
26 This program follows the usual GNU command line syntax, with long options
27 starting with two dashes (--). A summary of options is included below.
29 -i, --input source Run analysis on this audio file. Most uncompressed and
30 compressed are supported, depending on how aubio was built.
32 -o, --output sink Save results in this file. The file will be created on
33 the model of the input file. Onset times are marked by a short wood-block
36 -r, --samplerate rate Fetch the input source, resampled at the given
37 sampling rate. The rate should be specified in Hertz as an integer. If 0,
38 the sampling rate of the original source will be used. Defaults to 0.
40 -B, --bufsize win The size of the buffer to analyze, that is the length
41 of the window used for spectral and temporal computations. Defaults to 512.
43 -H, --hopsize hop The number of samples between two consecutive analysis.
46 -O, --onset method The onset detection method to use. See ONSET METHODS
47 below. Defaults to 'default'.
49 -t, --onset-threshold thres Set the threshold value for the onset peak
50 picking. Typical values are typically within 0.001 and 0.900. Defaults to
51 0.1. Lower threshold values imply more onsets detected. Try 0.5 in case of
52 over-detections. Defaults to 0.3.
54 -s, --silence sil Set the silence threshold, in dB, under which the pitch
55 will not be detected. A value of -20.0 would eliminate most onsets but the
56 loudest ones. A value of -90.0 would select all onsets. Defaults to -90.0.
58 -m, --mix-input Mix source signal to the output signal before writing to
61 -f, --force-overwrite Overwrite output file if it already exists.
63 -j, --jack Use Jack input/output. You will need a Jack connection
64 controller to feed aubio some signal and listen to its output.
66 -h, --help Print a short help message and exit.
68 -v, --verbose Be verbose.
72 Available methods are:
74 default Default distance, currently hfc
76 Default: 'default' (currently set to hfc)
78 energy Energy based distance
80 This function calculates the local energy of the input spectral frame.
82 hfc High-Frequency content
84 This method computes the High Frequency Content (HFC) of the input
85 spectral frame. The resulting function is efficient at detecting
88 Paul Masri. Computer modeling of Sound for Transformation and Synthesis of
89 Musical Signal. PhD dissertation, University of Bristol, UK, 1996.
91 complex Complex domain onset detection function
93 This function uses information both in frequency and in phase to determine
94 changes in the spectral content that might correspond to musical onsets.
95 It is best suited for complex signals such as polyphonic recordings.
97 Christopher Duxbury, Mike E. Davies, and Mark B. Sandler. Complex domain
98 onset detection for musical signals. In Proceedings of the Digital Audio
99 Effects Conference, DAFx-03, pages 90-93, London, UK, 2003.
101 phase Phase based onset detection function
103 This function uses information both in frequency and in phase to determine
104 changes in the spectral content that might correspond to musical onsets. It
105 is best suited for complex signals such as polyphonic recordings.
107 Juan-Pablo Bello, Mike P. Davies, and Mark B. Sandler. Phase-based note
108 onset detection for music signals. In Proceedings of the IEEE International
109 Conference on Acoustics Speech and Signal Processing, pages 441444,
112 specdiff Spectral difference onset detection function
114 Jonhatan Foote and Shingo Uchihashi. The beat spectrum: a new approach to
115 rhythm analysis. In IEEE International Conference on Multimedia and Expo
116 (ICME 2001), pages 881884, Tokyo, Japan, August 2001.
118 kl Kulback-Liebler onset detection function
120 Stephen Hainsworth and Malcom Macleod. Onset detection in music audio
121 signals. In Proceedings of the International Computer Music Conference
122 (ICMC), Singapore, 2003.
124 mkl Modified Kulback-Liebler onset detection function
126 Paul Brossier, ``Automatic annotation of musical audio for interactive
127 systems'', Chapter 2, Temporal segmentation, PhD thesis, Centre for
128 Digital music, Queen Mary University of London, London, UK, 2006.
130 specflux Spectral flux
132 Simon Dixon, Onset Detection Revisited, in ``Proceedings of the 9th
133 International Conference on Digital Audio Effects'' (DAFx-06), Montreal,
148 This manual page was written by Paul Brossier <piem@aubio.org>. Permission is
149 granted to copy, distribute and/or modify this document under the terms of
150 the GNU General Public License as published by the Free Software Foundation,
151 either version 3 of the License, or (at your option) any later version.