source: doc/aubiomfcc.txt @ 88d3d31

feature/autosinkfeature/cnnfeature/cnn_orgfeature/constantqfeature/crepefeature/crepe_orgfeature/pitchshiftfeature/pydocstringsfeature/timestretchfix/ffmpeg5
Last change on this file since 88d3d31 was dec8b9d, checked in by Paul Brossier <piem@piem.org>, 6 years ago

[doc] update Auditory Toolbox url

  • Property mode set to 100644
File size: 2.2 KB
Line 
1NAME
2  aubiomfcc - a command line tool to compute Mel-Frequency Cepstrum Coefficients
3
4SYNOPSIS
5
6  aubiomfcc source
7  aubiomfcc [[-i] source]
8            [-r rate] [-B win] [-H hop]
9            [-T time-format]
10            [-v] [-h]
11
12DESCRIPTION
13
14  aubiomfcc compute the Mel-Frequency Cepstrum Coefficients (MFCC).
15
16  MFCCs are coefficients that make up for the mel-frequency spectrum, a
17  representation of the short-term power spectrum of a sound. By default, 13
18  coefficients are computed using 40 filters.
19
20  When started with an input source (-i/--input), the coefficients are given on
21  the console, prefixed by their timestamps in seconds.
22
23OPTIONS
24
25  This program follows the usual GNU command line syntax, with long options
26  starting with two dashes (--). A summary of options is included below.
27
28  -i, --input source  Run analysis on this audio file. Most uncompressed and
29  compressed are supported, depending on how aubio was built.
30
31  -r, --samplerate rate  Fetch the input source, resampled at the given
32  sampling rate. The rate should be specified in Hertz as an integer. If 0,
33  the sampling rate of the original source will be used. Defaults to 0.
34
35  -B, --bufsize win  The size of the buffer to analyze, that is the length
36  of the window used for spectral and temporal computations. Defaults to 512.
37
38  -H, --hopsize hop  The number of samples between two consecutive analysis.
39  Defaults to 256.
40
41  -T, --timeformat format  Set time format (samples, ms, seconds). Defaults to
42  seconds.
43
44  -h, --help  Print a short help message and exit.
45
46  -v, --verbose  Be verbose.
47
48REFERENCES
49
50  Using the default parameters, the filter coefficients will be computed
51  according to Malcolm Slaney's Auditory Toolbox, available at the following
52  url:
53
54  https://engineering.purdue.edu/~malcolm/interval/1998-010/ (see file mfcc.m)
55
56SEE ALSO
57
58  aubioonset(1),
59  aubiopitch(1),
60  aubiotrack(1),
61  aubionotes(1),
62  aubioquiet(1),
63  and
64  aubiocut(1).
65
66AUTHOR
67
68  This manual page was written by Paul Brossier <piem@aubio.org>. Permission is
69  granted to copy, distribute and/or modify this document under the terms of
70  the GNU General Public License as published by the Free Software Foundation,
71  either version 3 of the License, or (at your option) any later version.
Note: See TracBrowser for help on using the repository browser.