source: doc/aubioonset.txt @ a1cce65

feature/autosinkfeature/cnnfeature/cnn_orgfeature/constantqfeature/crepefeature/crepe_orgfeature/pitchshiftfeature/pydocstringsfeature/timestretchfix/ffmpeg5
Last change on this file since a1cce65 was 29a5e27, checked in by Paul Brossier <piem@piem.org>, 7 years ago

doc/aubio{track,onset}.txt: update --miditap-note to -N

  • Property mode set to 100644
File size: 5.8 KB
Line 
1NAME
2  aubioonset - a command line tool to extract musical onset times
3
4SYNOPSIS
5
6  aubioonset source
7  aubioonset [[-i] source] [-o sink]
8             [-r rate] [-B win] [-H hop]
9             [-O method] [-t thres]
10             [-T time-format]
11             [-s sil] [-m] [-f]
12             [-j] [-N miditap-note] [-V miditap-velo]
13             [-v] [-h]
14
15DESCRIPTION
16
17  aubioonset attempts to detect onset times, the beginning of discrete sound
18  events, in audio signals.
19
20  When started with an input source (-i/--input), the detected onset times are
21  given on the console, in seconds.
22
23  When started without an input source, or with the jack option (-j/--jack),
24  aubioonset starts in jack mode.
25
26OPTIONS
27
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.
30
31  -i, --input source  Run analysis on this audio file. Most uncompressed and
32  compressed are supported, depending on how aubio was built.
33
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
36  like sound.
37
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.
41
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.
44
45  -H, --hopsize hop  The number of samples between two consecutive analysis.
46  Defaults to 256.
47
48  -O, --onset method  The onset detection method to use. See ONSET METHODS
49  below. Defaults to 'default'.
50
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.
55
56  -M, --minioi value  Set the minimum inter-onset interval, in seconds, the
57  shortest interval between two consecutive onsets. Defaults to 0.020
58
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.
62
63  -T, --timeformat format  Set time format (samples, ms, seconds). Defaults to
64  seconds.
65
66  -m, --mix-input  Mix source signal to the output signal before writing to
67  sink.
68
69  -f, --force-overwrite  Overwrite output file if it already exists.
70
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.
73
74  -N, --miditap-note  Override note value for MIDI tap. Defaults to 69.
75
76  -V, --miditap-velop  Override velocity value for MIDI tap. Defaults to 65.
77
78  -h, --help  Print a short help message and exit.
79
80  -v, --verbose  Be verbose.
81
82ONSET METHODS
83
84  Available methods are:
85
86  default  Default distance, currently hfc
87
88  Default: 'default' (currently set to hfc)
89
90  energy  Energy based distance
91
92  This function calculates the local energy of the input spectral frame.
93
94  hfc  High-Frequency content
95
96  This method computes the High Frequency Content (HFC) of the input
97  spectral frame. The resulting function is efficient at detecting
98  percussive onsets.
99
100  Paul Masri. Computer modeling of Sound for Transformation and Synthesis of
101  Musical Signal. PhD dissertation, University of Bristol, UK, 1996.
102
103  complex  Complex domain onset detection function
104
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.
108
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.
112
113  phase  Phase based onset detection function
114
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.
118
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,
122  Hong-Kong, 2003.
123
124  specdiff  Spectral difference onset detection function
125
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.
129
130  kl  Kulback-Liebler onset detection function
131
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.
135
136  mkl  Modified Kulback-Liebler onset detection function
137
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.
141
142  specflux  Spectral flux
143
144  Simon Dixon, Onset Detection Revisited, in ``Proceedings of the 9th
145  International Conference on Digital Audio Effects'' (DAFx-06), Montreal,
146  Canada, 2006.
147
148SEE ALSO
149
150  aubiopitch(1),
151  aubiotrack(1),
152  aubionotes(1),
153  aubioquiet(1),
154  aubiomfcc(1),
155  and
156  aubiocut(1).
157
158AUTHOR
159
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.
Note: See TracBrowser for help on using the repository browser.