2 aubioonset - a command line tool to extract musical onset times
7 aubioonset [[-i] source] [-o sink]
8 [-r rate] [-B win] [-H hop]
12 [-j] [-N miditap-note] [-V miditap-velo]
17 aubioonset attempts to detect onset times, the beginning of discrete sound
18 events, in audio signals.
20 When started with an input source (-i/--input), the detected onset times are
21 given on the console, in seconds.
23 When started without an input source, or with the jack option (-j/--jack),
24 aubioonset starts in jack mode.
28 This program follows the usual GNU command line syntax, with long options
29 starting with two dashes (--). A summary of options is included below.
31 -i, --input source Run analysis on this audio file. Most uncompressed and
32 compressed are supported, depending on how aubio was built.
34 -o, --output sink Save results in this file. The file will be created on
35 the model of the input file. Onset times are marked by a short wood-block
38 -r, --samplerate rate Fetch the input source, resampled at the given
39 sampling rate. The rate should be specified in Hertz as an integer. If 0,
40 the sampling rate of the original source will be used. Defaults to 0.
42 -B, --bufsize win The size of the buffer to analyze, that is the length
43 of the window used for spectral and temporal computations. Defaults to 512.
45 -H, --hopsize hop The number of samples between two consecutive analysis.
48 -O, --onset method The onset detection method to use. See ONSET METHODS
49 below. Defaults to 'default'.
51 -t, --onset-threshold thres Set the threshold value for the onset peak
52 picking. Values are typically in the range [0.001, 0.900]. Lower threshold
53 values imply more onsets detected. Increasing this threshold should reduce
54 the number of incorrect detections. Defaults to 0.3.
56 -M, --minioi value Set the minimum inter-onset interval, in seconds, the
57 shortest interval between two consecutive onsets. Defaults to 0.020
59 -s, --silence sil Set the silence threshold, in dB, under which the onset
60 will not be detected. A value of -20.0 would eliminate most onsets but the
61 loudest ones. A value of -90.0 would select all onsets. Defaults to -90.0.
63 -T, --timeformat format Set time format (samples, ms, seconds). Defaults to
66 -m, --mix-input Mix source signal to the output signal before writing to
69 -f, --force-overwrite Overwrite output file if it already exists.
71 -j, --jack Use Jack input/output. You will need a Jack connection
72 controller to feed aubio some signal and listen to its output.
74 -N, --miditap-note Override note value for MIDI tap. Defaults to 69.
76 -V, --miditap-velop Override velocity value for MIDI tap. Defaults to 65.
78 -h, --help Print a short help message and exit.
80 -v, --verbose Be verbose.
84 Available methods are:
86 default Default distance, currently hfc
88 Default: 'default' (currently set to hfc)
90 energy Energy based distance
92 This function calculates the local energy of the input spectral frame.
94 hfc High-Frequency content
96 This method computes the High Frequency Content (HFC) of the input
97 spectral frame. The resulting function is efficient at detecting
100 Paul Masri. Computer modeling of Sound for Transformation and Synthesis of
101 Musical Signal. PhD dissertation, University of Bristol, UK, 1996.
103 complex Complex domain onset detection function
105 This function uses information both in frequency and in phase to determine
106 changes in the spectral content that might correspond to musical onsets.
107 It is best suited for complex signals such as polyphonic recordings.
109 Christopher Duxbury, Mike E. Davies, and Mark B. Sandler. Complex domain
110 onset detection for musical signals. In Proceedings of the Digital Audio
111 Effects Conference, DAFx-03, pages 90-93, London, UK, 2003.
113 phase Phase based onset detection function
115 This function uses information both in frequency and in phase to determine
116 changes in the spectral content that might correspond to musical onsets. It
117 is best suited for complex signals such as polyphonic recordings.
119 Juan-Pablo Bello, Mike P. Davies, and Mark B. Sandler. Phase-based note
120 onset detection for music signals. In Proceedings of the IEEE International
121 Conference on Acoustics Speech and Signal Processing, pages 441444,
124 specdiff Spectral difference onset detection function
126 Jonhatan Foote and Shingo Uchihashi. The beat spectrum: a new approach to
127 rhythm analysis. In IEEE International Conference on Multimedia and Expo
128 (ICME 2001), pages 881884, Tokyo, Japan, August 2001.
130 kl Kulback-Liebler onset detection function
132 Stephen Hainsworth and Malcom Macleod. Onset detection in music audio
133 signals. In Proceedings of the International Computer Music Conference
134 (ICMC), Singapore, 2003.
136 mkl Modified Kulback-Liebler onset detection function
138 Paul Brossier, ``Automatic annotation of musical audio for interactive
139 systems'', Chapter 2, Temporal segmentation, PhD thesis, Centre for
140 Digital music, Queen Mary University of London, London, UK, 2006.
142 specflux Spectral flux
144 Simon Dixon, Onset Detection Revisited, in ``Proceedings of the 9th
145 International Conference on Digital Audio Effects'' (DAFx-06), Montreal,
160 This manual page was written by Paul Brossier <piem@aubio.org>. Permission is
161 granted to copy, distribute and/or modify this document under the terms of
162 the GNU General Public License as published by the Free Software Foundation,
163 either version 3 of the License, or (at your option) any later version.