| 1 | NAME |
|---|
| 2 | aubiomfcc - a command line tool to compute Mel-Frequency Cepstrum Coefficients |
|---|
| 3 | |
|---|
| 4 | SYNOPSIS |
|---|
| 5 | |
|---|
| 6 | aubiomfcc source |
|---|
| 7 | aubiomfcc [[-i] source] |
|---|
| 8 | [-r rate] [-B win] [-H hop] |
|---|
| 9 | [-T time-format] |
|---|
| 10 | [-v] [-h] |
|---|
| 11 | |
|---|
| 12 | DESCRIPTION |
|---|
| 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 | |
|---|
| 23 | OPTIONS |
|---|
| 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 | |
|---|
| 48 | REFERENCES |
|---|
| 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 | http://cobweb.ecn.purdue.edu/~malcolm/interval/1998-010/ (see file mfcc.m) |
|---|
| 55 | |
|---|
| 56 | SEE ALSO |
|---|
| 57 | |
|---|
| 58 | aubioonset(1), |
|---|
| 59 | aubiopitch(1), |
|---|
| 60 | aubiotrack(1), |
|---|
| 61 | aubionotes(1), |
|---|
| 62 | aubioquiet(1), |
|---|
| 63 | and |
|---|
| 64 | aubiocut(1). |
|---|
| 65 | |
|---|
| 66 | AUTHOR |
|---|
| 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. |
|---|
