diff options
Diffstat (limited to 'libraries/aubio/man/aubiomfcc.1')
| -rw-r--r-- | libraries/aubio/man/aubiomfcc.1 | 89 |
1 files changed, 89 insertions, 0 deletions
diff --git a/libraries/aubio/man/aubiomfcc.1 b/libraries/aubio/man/aubiomfcc.1 new file mode 100644 index 0000000000..e8f21ea7f0 --- /dev/null +++ b/libraries/aubio/man/aubiomfcc.1 @@ -0,0 +1,89 @@ +.\" Text automatically generated by txt2man +.TH AUBIOMFCC 1 "22 July 2023" "aubio 0.4.9" "aubio User's manual" +.SH NAME +\fBaubiomfcc \fP- a command line tool to compute Mel-Frequency Cepstrum Coefficients +\fB +.SH SYNOPSIS +.nf +.fam C + +\fBaubiomfcc\fP \fIsource\fP +\fBaubiomfcc\fP [[\fB-i\fP] \fIsource\fP] + [\fB-r\fP \fIrate\fP] [\fB-B\fP \fIwin\fP] [\fB-H\fP \fIhop\fP] + [\fB-T\fP \fItime-format\fP] + [\fB-v\fP] [\fB-h\fP] + +.fam T +.fi +.fam T +.fi +.SH DESCRIPTION + +\fBaubiomfcc\fP compute the Mel-Frequency Cepstrum Coefficients (MFCC). +.PP +MFCCs are coefficients that make up for the mel-frequency spectrum, a +representation of the short-term power spectrum of a sound. By default, 13 +coefficients are computed using 40 filters. +.PP +When started with an input \fIsource\fP (\fB-i\fP/\fB--input\fP), the coefficients are given on +the console, prefixed by their timestamps in seconds. +.SH OPTIONS + +This program follows the usual GNU command line syntax, with long options +starting with two dashes (--). A summary of options is included below. +.TP +.B +\fB-i\fP, \fB--input\fP \fIsource\fP +Run analysis on this audio file. Most uncompressed and +compressed are supported, depending on how aubio was built. +.TP +.B +\fB-r\fP, \fB--samplerate\fP \fIrate\fP +Fetch the input \fIsource\fP, resampled at the given +sampling \fIrate\fP. The \fIrate\fP should be specified in Hertz as an integer. If 0, +the sampling \fIrate\fP of the original \fIsource\fP will be used. Defaults to 0. +.TP +.B +\fB-B\fP, \fB--bufsize\fP \fIwin\fP +The size of the buffer to analyze, that is the length +of the window used for spectral and temporal computations. Defaults to 512. +.TP +.B +\fB-H\fP, \fB--hopsize\fP \fIhop\fP +The number of samples between two consecutive analysis. +Defaults to 256. +.TP +.B +\fB-T\fP, \fB--timeformat\fP format +Set time format (samples, ms, seconds). Defaults to +seconds. +.TP +.B +\fB-h\fP, \fB--help\fP +Print a short help message and exit. +.TP +.B +\fB-v\fP, \fB--verbose\fP +Be verbose. +.SH REFERENCES + +Using the default parameters, the filter coefficients will be computed +according to Malcolm Slaney's Auditory Toolbox, available at the following +url: +.PP +https://engineering.purdue.edu/~malcolm/interval/1998-010/ (see file mfcc.m) +.SH SEE ALSO + +\fBaubioonset\fP(1), +\fBaubiopitch\fP(1), +\fBaubiotrack\fP(1), +\fBaubionotes\fP(1), +\fBaubioquiet\fP(1), +and +\fBaubiocut\fP(1). +.SH AUTHOR + +This manual page was written by Paul Brossier <piem@aubio.org>. Permission is +granted to copy, distribute and/or modify this document under the terms of +the GNU General Public License as published by the Free Software Foundation, +either version 3 of the License, or (at your option) any later version. |