source: doc/aubioonset.txt @ 664fd25

feature/autosinkfeature/cnnfeature/cnn_orgfeature/constantqfeature/crepefeature/crepe_orgfeature/pitchshiftfeature/pydocstringsfeature/timestretchfix/ffmpeg5pitchshiftsamplertimestretchyinfft+
Last change on this file since 664fd25 was 664fd25, checked in by Paul Brossier <piem@piem.org>, 11 years ago

doc/: document -f --force-overwrite option

  • Property mode set to 100644
File size: 5.4 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             [-s sil] [-m] [-f]
11             [-j] [-v] [-h]
12
13DESCRIPTION
14
15  aubioonset attempts to detect onset times, the beginning of discrete sound
16  events, in audio signals.
17
18  When started with an input source (-i/--input), the detected onset times are
19  given on the console, in seconds.
20
21  When started without an input source, or with the jack option (-j/--jack),
22  aubioonset starts in jack mode.
23
24OPTIONS
25
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.
28
29  -i, --input source  Run analysis on this audio file. Most uncompressed and
30  compressed are supported, depending on how aubio was built.
31
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
34  like sound.
35
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.
39
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.
42
43  -H, --hopsize hop  The number of samples between two consecutive analysis.
44  Defaults to 256.
45
46  -O, --onset method  The onset detection method to use. See ONSET METHODS
47  below. Defaults to 'default'.
48
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.
53
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.
57
58  -m, --mix-input  Mix source signal to the output signal before writing to
59  sink.
60
61  -f, --force-overwrite  Overwrite output file if it already exists.
62
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.
65
66  -h, --help  Print a short help message and exit.
67
68  -v, --verbose  Be verbose.
69
70ONSET METHODS
71
72  Available methods are:
73
74  default  Default distance, currently hfc
75
76  Default: 'default' (currently set to hfc)
77
78  energy  Energy based distance
79
80  This function calculates the local energy of the input spectral frame.
81
82  hfc  High-Frequency content
83
84  This method computes the High Frequency Content (HFC) of the input
85  spectral frame. The resulting function is efficient at detecting
86  percussive onsets.
87
88  Paul Masri. Computer modeling of Sound for Transformation and Synthesis of
89  Musical Signal. PhD dissertation, University of Bristol, UK, 1996.
90
91  complex  Complex domain onset detection function
92
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.
96
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.
100
101  phase  Phase based onset detection function
102
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.
106
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,
110  Hong-Kong, 2003.
111
112  specdiff  Spectral difference onset detection function
113
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.
117
118  kl  Kulback-Liebler onset detection function
119
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.
123
124  mkl  Modified Kulback-Liebler onset detection function
125
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.
129
130  specflux  Spectral flux
131
132  Simon Dixon, Onset Detection Revisited, in ``Proceedings of the 9th
133  International Conference on Digital Audio Effects'' (DAFx-06), Montreal,
134  Canada, 2006.
135
136SEE ALSO
137
138  aubiopitch(1),
139  aubiotrack(1),
140  aubionotes(1),
141  aubioquiet(1),
142  aubiomfcc(1),
143  and
144  aubiocut(1).
145
146AUTHOR
147
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.
Note: See TracBrowser for help on using the repository browser.