Man Linux: Main Page and Category List

NAME

       aubiocut  —  a command line tool to extract onsets and tempo from sound
       files.

SYNOPSIS

       aubiocut [options] -i soundfile

DESCRIPTION

       aubiocut attempts to detect onset times,  the  beginning  of  discreted
       sound events, or beat locations, in audio signals.

       When  using  the  --cut  option, aubiocut takes an input sound file and
       produce small files sliced at onset locations (or silences). The slices
       can then be sent for example to a player, a sequencer, or a sampler.

       A plotting module is available via the Gnuplot Python package.

OPTIONS

       This  program  follows  the  usual  GNU  command line syntax, with long
       options starting with two  dashes  (‘-’).   A  summary  of  options  is
       included below.

       -i   --input filein
                 input sound file

       -m   --mode onset_detection_mode
                 onset          detection          mode         [default=dual]
                 complexdomain|hfc|phase|specdiff|energy|kl|mkl|dual

       -b   --beat
                 detect beats and output beat locations

       -B   --bufsize=BUFSIZE
                 buffer size [default=512]

       -H   --hopsize=HOPSIZE
                 overlap size [default=256]

       -t   --threshold=THRESHOLD
                 onset peak picking threshold [default=0.3]

       -C   --dcthreshold=DCTHRESHOLD
                 onset peak picking DC component [default=1.]

       -s   --silence=SILENCE
                 silence threshold [default=-70]

       -M   --mintol=MINIOI
                 minimum inter onset interval [default=0.048s]

       -D   --delay=DELAY
                 number of  seconds  to  take  back  [default=system]  default
                 system delay is 3*hopsize/samplerate

       -L   --localmin
                 use local minima after peak detection

       -c   --cut
                 cut  input  sound  file  at  detected  labels (best used with
                 option -L)

       -d   --derivate
                 derivate onset detection function

       -S   --silencecut
                 outputs silence locations instead of onset locations

       -z   --zerocross=ZEROTHRES
                 zero-crossing threshold for slicing [default=0.00008]

       -f   --function
                 print detection function

       -q   --quiet
                 be quiet

       -h   --help
                 Show a summary of options.

       -v   --verbose
                 make lots of noise [default]

   Plotting options
       When the Python  interface  to  Gnuplot  is  installed,  the  following
       additional options are available.

       -p   --plot
                 draw plot

       -n   --no-onsets
                 do not plot detected onsets, only detection functions

       -x   --xsize=SIZE
                 define horizontal plot size [default=1.]

       -y   --ysize=SIZE
                 define vertical plot size [default=1.]

       -O   --outplot=OUTPLOT
                 save plot to output.{ps,eps,png,svg} instead of displaying it

BUGS

       For now the program has only been tested on audio  signals  sampled  at
       44.1 kHz.

SEE ALSO

       aubioonset(1) aubiotrack(1) aubionotes(1) aubiopitch(1)

AUTHOR

       This  manual  page  was  written  by  Paul  Brossier (piem@altern.org).
       Permission is granted to copy, distribute and/or modify  this  document
       under  the terms of the GNU General Public License, Version 2 any later
       version published by the Free Software Foundation.

       On Debian systems, the complete text of the GNU General Public  License
       can be found in /usr/share/common-licenses/GPL.