Command line tools

The python module comes with the following tools:

  • aubio estimate and extract descriptors from sound files
  • aubiocut slices sound files at onset or beat timestamps

More command line tools are included along with the library.

  • aubioonset outputs the time stamp of detected note onsets
  • aubiopitch attempts to identify a fundamental frequency, or pitch, for each frame of the input sound
  • aubiomfcc computes Mel-frequency Cepstrum Coefficients
  • aubiotrack outputs the time stamp of detected beats
  • aubionotes emits midi-like notes, with an onset, a pitch, and a duration
  • aubioquiet extracts quiet and loud regions

aubio

NAME
  aubio - a command line tool to extract information from sound files

SYNOPSIS

  aubio [-h] [-V] <command> ...

COMMANDS

  The general syntax is "aubio <command> <soundfile> [options]". The following
  commands are available:

  onset        get onset times
  pitch        extract fundamental frequency
  beat         get locations of beats
  tempo        get overall tempo in bpm
  notes        get midi-like notes
  mfcc         extract mel-frequency cepstrum coefficients
  melbands     extract mel-frequency energies per band

  For a list of available commands, use "aubio -h". For more info about each
  command, use "aubio <command> --help".

GENERAL OPTIONS

  These options can be used before any command has been specified.

  -h, --help  show help message and exit

  -V, --version  show version

COMMON OPTIONS

  The following options can be used with all commands:

  <source_uri>, -i <source_uri>, --input <source_uri>  input sound file to
  analyse (required)

  -r <freq>, --samplerate <freq>  samplerate at which the file should be
  represented (default: 0, e.g. samplerate of the input sound)

  -H <size>, --hopsize <size>  overlap size, number of samples between two
  consecutive analysis (default: 256)

  -B <size>, --bufsize <size>  buffer size, number of samples used for each
  analysis, (e.g. FFT length, default: 512)

  -h, --help  show help message and exit

  -T format, --time-format format  select time values output format (samples,
  ms, seconds) (default: seconds)

  -v, --verbose  be verbose (increment verbosity by 1, default: 1)

  -q, --quiet  be quiet (set verbosity to 0)

ONSET

  The following additional options can be used with the "onset" subcommand.

  -m <method>, --method <method>  onset novelty function
  <default|energy|hfc|complex|phase|specdiff|kl|mkl|specflux> (default:
  default)

  -t <threshold>, --threshold <threshold>  threshold (default: unset)

  -s <value>, --silence <value>  silence threshold, in dB (default: -70)

  -M <value>, --minioi <value>  minimum Inter-Onset Interval (default: 12ms)

PITCH

  The following additional options can be used with the "pitch" subcommand.

  -m <method>, --method <method>  pitch detection method
  <default|yinfft|yin|mcomb|fcomb|schmitt> (default: default, e.g. yinfft)

  -t <threshold>, --threshold <threshold>  tolerance (default: unset)

  -s <value>, --silence <value>  silence threshold, in dB (default: -70)

  The default buffer size for the beat algorithm is 2048. The default hop size
  is 256.

BEAT

  The "beat" command accepts all common options and no additional options.

  The default buffer size for the beat algorithm is 1024. The default hop size
  is 512.

TEMPO

  The "tempo" command accepts all common options and no additional options.

  The default buffer size for the beat algorithm is 1024. The default hop size
  is 512.

NOTES

  The following additional options can be used with the "notes" subcommand.

  -s <value>, --silence <value>  silence threshold, in dB (default: -70)

  -d <value>, --release-drop <value>  release drop level, in dB. If the level
  drops more than this amount since the last note started, the note will be
  turned off (default: 10).

MFCC

  The "mfcc" command accepts all common options and no additional options.

MELBANDS

  The "melbands" command accepts all common options and no additional options.

EXAMPLES

  Extract onsets using a minimum inter-onset interval of 30ms:

    aubio onset /path/to/input_file -M 30ms

  Extract pitch with method "mcomb" and a silence threshold of -90dB:

    aubio pitch /path/to/input_file -m mcomb -s -90.0

  Extract MFCC using the standard Slaney implementation:

    aubio mfcc /path/to/input_file -r 44100


SEE ALSO

  aubiocut(1)

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.

aubiocut

NAME
  aubiocut - a command line tool to slice sound files at onset or beat timestamps

SYNOPSIS

  aubiocut source
  aubiocut [[-i] source]
           [-r rate] [-B win] [-H hop]
           [-O method] [-t thres]
           [-b] [-c]
           [-v] [-q] [-h]

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 source  Run analysis on this audio file. Most uncompressed and
  compressed are supported, depending on how aubio was built.

  -r, --samplerate rate  Fetch the input source, resampled at the given
  sampling rate. The rate should be specified in Hertz as an integer. If set
  to 0, the sampling rate of the original source will be used. Defaults to 0.

  -B, --bufsize win  The size of the buffer to analyze, that is the length
  of the window used for spectral and temporal computations. Defaults to 512.

  -H, --hopsize hop  The number of samples between two consecutive analysis.
  Defaults to 256.

  -O, --onset method  The onset detection method to use. See ONSET METHODS
  below. Defaults to 'default'.

  -b, --beat  Use beat locations instead of onset locations.

  -t, --onset-threshold thres  Set the threshold value for the onset peak
  picking. Values are typically in the range [0.001, 0.900]. Lower threshold
  values imply more onsets detected. Increasing this threshold should reduce
  the number of incorrect detections. Defaults to 0.3.

  -c, --cut  Cut input sound file at detected labels. A new sound files for
  each slice will be created in the current directory.

  -o, --output directory  Specify the directory path where slices of the
  original source should be created.

  --cut-until-nsamples n  How many extra samples should be added at the end of
  each slice (default 0).

  --cut-until-nslices n  How many extra slices should be added at the end of
  each slice (default 0).

  --create-first  Alway create first slice.

  -h, --help  Print a short help message and exit.

  -v, --verbose  Be verbose.

  -q, --quiet  Be quiet.


ONSET METHODS

  Available methods: default, energy, hfc, complex, phase, specdiff, kl, mkl,
  specflux.

  See aubioonset(1) for details about these methods.


SEE ALSO

  aubioonset(1),
  aubiopitch(1),
  aubiotrack(1),
  aubionotes(1),
  aubioquiet(1),
  and
  aubiomfcc(1).

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.

aubioonset

NAME
  aubioonset - a command line tool to extract musical onset times

SYNOPSIS

  aubioonset source
  aubioonset [[-i] source] [-o sink]
             [-r rate] [-B win] [-H hop]
             [-O method] [-t thres]
             [-T time-format]
             [-s sil] [-m] [-f]
             [-j] [-N miditap-note] [-V miditap-velo]
             [-v] [-h]

DESCRIPTION

  aubioonset attempts to detect onset times, the beginning of discrete sound
  events, in audio signals.

  When started with an input source (-i/--input), the detected onset times are
  given on the console, in seconds.

  When started without an input source, or with the jack option (-j/--jack),
  aubioonset starts in jack mode.

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 source  Run analysis on this audio file. Most uncompressed and
  compressed are supported, depending on how aubio was built.

  -o, --output sink  Save results in this file. The file will be created on
  the model of the input file. Onset times are marked by a short wood-block
  like sound.

  -r, --samplerate rate  Fetch the input source, resampled at the given
  sampling rate. The rate should be specified in Hertz as an integer. If 0,
  the sampling rate of the original source will be used. Defaults to 0.

  -B, --bufsize win  The size of the buffer to analyze, that is the length
  of the window used for spectral and temporal computations. Defaults to 512.

  -H, --hopsize hop  The number of samples between two consecutive analysis.
  Defaults to 256.

  -O, --onset method  The onset detection method to use. See ONSET METHODS
  below. Defaults to 'default'.

  -t, --onset-threshold thres  Set the threshold value for the onset peak
  picking. Values are typically in the range [0.001, 0.900]. Lower threshold
  values imply more onsets detected. Increasing this threshold should reduce
  the number of incorrect detections. Defaults to 0.3.

  -M, --minioi value  Set the minimum inter-onset interval, in seconds, the
  shortest interval between two consecutive onsets. Defaults to 0.020

  -s, --silence sil  Set the silence threshold, in dB, under which the onset
  will not be detected. A value of -20.0 would eliminate most onsets but the
  loudest ones. A value of -90.0 would select all onsets. Defaults to -90.0.

  -T, --timeformat format  Set time format (samples, ms, seconds). Defaults to
  seconds.

  -m, --mix-input  Mix source signal to the output signal before writing to
  sink.

  -f, --force-overwrite  Overwrite output file if it already exists.

  -j, --jack  Use Jack input/output. You will need a Jack connection
  controller to feed aubio some signal and listen to its output.

  -N, --miditap-note  Override note value for MIDI tap. Defaults to 69.

  -V, --miditap-velop  Override velocity value for MIDI tap. Defaults to 65.

  -h, --help  Print a short help message and exit.

  -v, --verbose  Be verbose.

ONSET METHODS

  Available methods are:

  default  Default distance, currently hfc

  Default: 'default' (currently set to hfc)

  energy  Energy based distance

  This function calculates the local energy of the input spectral frame.

  hfc  High-Frequency content

  This method computes the High Frequency Content (HFC) of the input
  spectral frame. The resulting function is efficient at detecting
  percussive onsets.

  Paul Masri. Computer modeling of Sound for Transformation and Synthesis of
  Musical Signal. PhD dissertation, University of Bristol, UK, 1996.

  complex  Complex domain onset detection function

  This function uses information both in frequency and in phase to determine
  changes in the spectral content that might correspond to musical onsets.
  It is best suited for complex signals such as polyphonic recordings.

  Christopher Duxbury, Mike E. Davies, and Mark B. Sandler.  Complex domain
  onset detection for musical signals. In Proceedings of the Digital Audio
  Effects Conference, DAFx-03, pages 90-93, London, UK, 2003.

  phase  Phase based onset detection function

  This function uses information both in frequency and in phase to determine
  changes in the spectral content that might correspond to musical onsets. It
  is best suited for complex signals such as polyphonic recordings.

  Juan-Pablo Bello, Mike P. Davies, and Mark B. Sandler.  Phase-based note
  onset detection for music signals. In Proceedings of the IEEE International
  Conference on Acoustics Speech and Signal Processing, pages 441­444,
  Hong-Kong, 2003.

  specdiff  Spectral difference onset detection function

  Jonhatan Foote and Shingo Uchihashi. The beat spectrum: a new approach to
  rhythm analysis. In IEEE International Conference on Multimedia and Expo
  (ICME 2001), pages 881­884, Tokyo, Japan, August 2001.

  kl  Kulback-Liebler onset detection function

  Stephen Hainsworth and Malcom Macleod. Onset detection in music audio
  signals. In Proceedings of the International Computer Music Conference
  (ICMC), Singapore, 2003.

  mkl  Modified Kulback-Liebler onset detection function

  Paul Brossier, ``Automatic annotation of musical audio for interactive
  systems'', Chapter 2, Temporal segmentation, PhD thesis, Centre for
  Digital music, Queen Mary University of London, London, UK, 2006.

  specflux  Spectral flux

  Simon Dixon, Onset Detection Revisited, in ``Proceedings of the 9th
  International Conference on Digital Audio Effects'' (DAFx-06), Montreal,
  Canada, 2006.

SEE ALSO

  aubiopitch(1),
  aubiotrack(1),
  aubionotes(1),
  aubioquiet(1),
  aubiomfcc(1),
  and
  aubiocut(1).

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.

aubiopitch

NAME
  aubiopitch - a command line tool to extract musical pitch

SYNOPSIS

  aubiopitch source
  aubiopitch [[-i] source] [-o sink]
             [-r rate] [-B win] [-H hop]
             [-p method] [-u unit] [-l thres]
             [-T time-format]
             [-s sil] [-f]
             [-v] [-h] [-j]

DESCRIPTION

  aubiopitch attempts to detect the pitch, the perceived height of a musical
  note.

  When started with an input source (-i/--input), the detected pitch are
  printed on the console, prefixed by a timestamp in seconds. If no pitch
  candidate is found, the output is 0.

  When started without an input source, or with the jack option (-j/--jack),
  aubiopitch starts in jack mode.

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 source  Run analysis on this audio file. Most uncompressed and
  compressed are supported, depending on how aubio was built.

  -o, --output sink  Save results in this file. The file will be created on
  the model of the input file. The detected frequency is played at the
  detected loudness.

  -r, --samplerate rate  Fetch the input source, resampled at the given
  sampling rate. The rate should be specified in Hertz as an integer. If 0,
  the sampling rate of the original source will be used. Defaults to 0.

  -B, --bufsize win  The size of the buffer to analyze, that is the length
  of the window used for spectral and temporal computations. Defaults to 2048.

  -H, --hopsize hop  The number of samples between two consecutive analysis.
  Defaults to 256.

  -p, --pitch method  The pitch detection method to use. See PITCH METHODS
  below. Defaults to 'default'.

  -u, --pitch-unit unit  The unit to be used to print frequencies. Possible
  values include midi, bin, cent, and Hz. Defaults to 'Hz'.

  -l, --pitch-tolerance thres  Set the tolerance for the pitch detection
  algorithm. Typical values range between 0.2 and 0.9. Pitch candidates found
  with a confidence less than this threshold will not be selected. The higher
  the threshold, the more confidence in the candidates. Defaults to unset.

  -s, --silence sil  Set the silence threshold, in dB, under which the onset
  will not be detected. A value of -20.0 would eliminate most onsets but the
  loudest ones. A value of -90.0 would select all onsets. Defaults to -90.0.

  -T, --timeformat format  Set time format (samples, ms, seconds). Defaults to
  seconds.

  -m, --mix-input  Mix source signal to the output signal before writing to
  sink.

  -f, --force-overwrite  Overwrite output file if it already exists.

  -j, --jack  Use Jack input/output. You will need a Jack connection
  controller to feed aubio some signal and listen to its output.

  -h, --help  Print a short help message and exit.

  -v, --verbose  Be verbose.

PITCH METHODS

  Available methods are:

  default  use the default method

  Currently, the default method is set to yinfft.

  schmitt  Schmitt trigger

  This pitch extraction method implements a Schmitt trigger to estimate the
  period of a signal. It is computationally very inexpensive, but also very
  sensitive to noise.

  fcomb  a fast harmonic comb filter

  This pitch extraction method implements a fast harmonic comb filter to
  determine the fundamental frequency of a harmonic sound.

  mcomb  multiple-comb filter

  This fundamental frequency estimation algorithm implements spectral
  flattening, multi-comb filtering and peak histogramming.

  specacf  Spectral auto-correlation function

  yin  YIN algorithm

  This algorithm was developed by A. de Cheveigne and H. Kawahara and
  was first published in:

  De Cheveigné, A., Kawahara, H. (2002) "YIN, a fundamental frequency
  estimator for speech and music", J. Acoust. Soc. Am. 111, 1917-1930.

  yinfft  Yinfft algorithm

  This algorithm was derived from the YIN algorithm. In this implementation, a
  Fourier transform is used to compute a tapered square difference function,
  which allows spectral weighting. Because the difference function is tapered,
  the selection of the period is simplified.

  Paul Brossier, Automatic annotation of musical audio for interactive systems,
  Chapter 3, Pitch Analysis, PhD thesis, Centre for Digital music, Queen Mary
  University of London, London, UK, 2006.

  yinfast  YIN algorithm (accelerated)

  An optimised implementation of the YIN algorithm, yielding results identical
  to the original YIN algorithm, while reducing its computational cost from
  O(n^2) to O(n log(n)).

SEE ALSO

  aubioonset(1),
  aubiotrack(1),
  aubionotes(1),
  aubioquiet(1),
  aubiomfcc(1),
  and
  aubiocut(1).

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.

aubiomfcc

NAME
  aubiomfcc - a command line tool to compute Mel-Frequency Cepstrum Coefficients

SYNOPSIS

  aubiomfcc source
  aubiomfcc [[-i] source]
            [-r rate] [-B win] [-H hop]
            [-T time-format]
            [-v] [-h]

DESCRIPTION

  aubiomfcc compute the Mel-Frequency Cepstrum Coefficients (MFCC).

  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.

  When started with an input source (-i/--input), the coefficients are given on
  the console, prefixed by their timestamps in seconds.

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 source  Run analysis on this audio file. Most uncompressed and
  compressed are supported, depending on how aubio was built.

  -r, --samplerate rate  Fetch the input source, resampled at the given
  sampling rate. The rate should be specified in Hertz as an integer. If 0,
  the sampling rate of the original source will be used. Defaults to 0.

  -B, --bufsize win  The size of the buffer to analyze, that is the length
  of the window used for spectral and temporal computations. Defaults to 512.

  -H, --hopsize hop  The number of samples between two consecutive analysis.
  Defaults to 256.

  -T, --timeformat format  Set time format (samples, ms, seconds). Defaults to
  seconds.

  -h, --help  Print a short help message and exit.

  -v, --verbose  Be verbose.

REFERENCES

  Using the default parameters, the filter coefficients will be computed
  according to Malcolm Slaney's Auditory Toolbox, available at the following
  url:

  https://engineering.purdue.edu/~malcolm/interval/1998-010/ (see file mfcc.m)

SEE ALSO

  aubioonset(1),
  aubiopitch(1),
  aubiotrack(1),
  aubionotes(1),
  aubioquiet(1),
  and
  aubiocut(1).

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.

aubiotrack

NAME
  aubiotrack - a command line tool to extract musical beats from audio signals

SYNOPSIS

  aubiotrack source
  aubiotrack [[-i] source] [-o sink]
             [-r rate] [-B win] [-H hop]
             [-T time-format]
             [-s sil] [-m]
             [-j] [-N miditap-note] [-V miditap-velo]
             [-v] [-h]

DESCRIPTION

  aubiotrack attempts to detect beats, the time where one would intuitively be
  tapping his foot.

  When started with an input source (-i/--input), the detected beats are given
  on the console, in seconds.

  When started without an input source, or with the jack option (-j/--jack),
  aubiotrack starts in jack mode.

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 source  Run analysis on this audio file. Most uncompressed and
  compressed are supported, depending on how aubio was built.

  -o, --output sink  Save results in this file. The file will be created on the
  model of the input file. Beats are marked by a short wood-block like sound.

  -r, --samplerate rate  Fetch the input source, resampled at the given
  sampling rate. The rate should be specified in Hertz as an integer. If 0,
  the sampling rate of the original source will be used. Defaults to 0.

  -B, --bufsize win  The size of the buffer to analyze, that is the length
  of the window used for spectral and temporal computations. Defaults to 512.

  -H, --hopsize hop  The number of samples between two consecutive analysis.
  Defaults to 256.

  -s, --silence sil  Set the silence threshold, in dB, under which the pitch
  will not be detected. A value of -20.0 would eliminate most onsets but the
  loudest ones. A value of -90.0 would select all onsets. Defaults to -90.0.

  -m, --mix-input  Mix source signal to the output signal before writing to
  sink.

  -f, --force-overwrite  Overwrite output file if it already exists.

  -j, --jack  Use Jack input/output. You will need a Jack connection
  controller to feed aubio some signal and listen to its output.

  -N, --miditap-note  Override note value for MIDI tap. Defaults to 69.

  -V, --miditap-velop  Override velocity value for MIDI tap. Defaults to 65.

  -T, --timeformat format  Set time format (samples, ms, seconds). Defaults to
  seconds.

  -h, --help  Print a short help message and exit.

  -v, --verbose  Be verbose.

BEAT TRACKING METHODS

  Aubio currently implements one the causal beat tracking algorithm designed by
  Matthew Davies and described in the following articles:

  Matthew E. P. Davies and Mark D. Plumbley. Causal tempo tracking of audio.
  In Proceedings of the International Symposium on Music Information Retrieval
  (ISMIR), pages 164­169, Barcelona, Spain, 2004.

  Matthew E. P. Davies, Paul Brossier, and Mark D. Plumbley. Beat tracking
  towards automatic musical accompaniment. In Proceedings of the Audio
  Engineering Society 118th Convention, Barcelona, Spain, May 2005.

SEE ALSO

  aubioonset(1),
  aubiopitch(1),
  aubionotes(1),
  aubioquiet(1),
  aubiomfcc(1),
  and
  aubiocut(1).

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.

aubionotes

NAME
  aubionotes - a command line tool to extract musical notes

SYNOPSIS

  aubionotes source
  aubionotes [[-i] source]
             [-r rate] [-B win] [-H hop]
             [-O method] [-t thres] [-d drop]
             [-p method] [-u unit] [-l thres]
             [-T time-format]
             [-s sil]
             [-j] [-v] [-h]

DESCRIPTION

  aubionotes attempts to detect notes by looking for note onsets and pitches.
  Consecutive events are segmented using onset detection, while a fundamental
  frequency extraction algorithm determines their pitch.

  When started with an input source (-i/--input), the detected notes are
  printed on standard output, in seconds and midi note number.

  When started without an input source, or with the jack option (-j/--jack),
  aubionotes starts in jack mode.

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 source  Run analysis on this audio file. Most uncompressed and
  compressed are supported, depending on how aubio was built.

  -r, --samplerate rate  Fetch the input source, resampled at the given
  sampling rate. The rate should be specified in Hertz as an integer. If 0,
  the sampling rate of the original source will be used. Defaults to 0.

  -B, --bufsize win  The size of the buffer to analyze, that is the length
  of the window used for spectral and temporal computations. Defaults to 512.

  -H, --hopsize hop  The number of samples between two consecutive analysis.
  Defaults to 256.

  -O, --onset method  The onset detection method to use. See ONSET METHODS
  below. Defaults to 'default'.

  -t, --onset-threshold thres  Set the threshold value for the onset peak
  picking. Typical values are typically within 0.001 and 0.900. Defaults to
  0.1. Lower threshold values imply more onsets detected. Try 0.5 in case of
  over-detections. Defaults to 0.3.

  -M, --minioi value  Set the minimum inter-onset interval, in seconds, the
  shortest interval between two consecutive notes. Defaults to 0.030

  -p, --pitch method  The pitch detection method to use. See PITCH METHODS
  below. Defaults to 'default'.

  -u, --pitch-unit unit  The unit to be used to print frequencies. Possible
  values include midi, bin, cent, and Hz. Defaults to 'Hz'.

  -l, --pitch-tolerance thres  Set the tolerance for the pitch detection
  algorithm. Typical values range between 0.2 and 0.9. Pitch candidates found
  with a confidence less than this threshold will not be selected. The higher
  the threshold, the more confidence in the candidates. Defaults to unset.

  -s, --silence sil  Set the silence threshold, in dB, under which the pitch
  will not be detected. A value of -20.0 would eliminate most onsets but the
  loudest ones. A value of -90.0 would select all onsets. Defaults to -90.0.

  -d, --release-drop  Set the release drop threshold, in dB. If the level drops
  more than this amount since the last note started, the note will be turned
  off. Defaults to 10.

  -T, --timeformat format  Set time format (samples, ms, seconds). Defaults to
  seconds.

  -j, --jack  Use Jack input/output. You will need a Jack connection
  controller to feed aubio some signal and listen to its output.

  -h, --help  Print a short help message and exit.

  -v, --verbose  Be verbose.

ONSET METHODS

  Available methods: default, energy, hfc, complex, phase, specdiff, kl, mkl,
  specflux.

  See aubioonset(1) for details about these methods.

PITCH METHODS

  Available methods: default, schmitt, fcomb, mcomb, specacf, yin, yinfft,
  yinfast.

  See aubiopitch(1) for details about these methods.

SEE ALSO

  aubioonset(1),
  aubiopitch(1),
  aubiotrack(1),
  aubioquiet(1),
  aubiomfcc(1),
  and
  aubiocut(1).

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.

aubioquiet

NAME
  aubioquiet - a command line tool to extracts quiet and loud regions from a file

SYNOPSIS

  aubioquiet source
  aubioquiet [[-i] source]
             [-r rate] [-B win] [-H hop]
             [-T time-format]
             [-s sil]
             [-v] [-h]

DESCRIPTION

  aubioquiet will print a timestamp each time it detects a new silent region or
  a new loud region in a sound file.

  When started with an input source (-i/--input), the detected timestamps are
  printed on the console, in seconds.

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 source  Run analysis on this audio file. Most uncompressed and
  compressed are supported, depending on how aubio was built.

  -r, --samplerate rate  Fetch the input source, resampled at the given
  sampling rate. The rate should be specified in Hertz as an integer. If 0,
  the sampling rate of the original source will be used. Defaults to 0.

  -B, --bufsize win  The size of the buffer to analyze, that is the length
  of the window used for spectral and temporal computations. Defaults to 512.

  -H, --hopsize hop  The number of samples between two consecutive analysis.
  Defaults to 256.

  -s, --silence sil  Set the silence threshold, in dB, under which the pitch
  will not be detected. Defaults to -90.0.

  -T, --timeformat format  Set time format (samples, ms, seconds). Defaults to
  seconds.

  -h, --help  Print a short help message and exit.

  -v, --verbose  Be verbose.

EXAMPLE OUTPUT

  NOISY: 28.775330

  QUIET: 28.914648


SEE ALSO

  aubioonset(1),
  aubiopitch(1),
  aubiotrack(1),
  aubionotes(1),
  aubiomfcc(1),
  and
  aubiocut(1).

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, Version 3 any later version published
  by the Free Software Foundation.

Command line features

feat vs. prg onset pitch mfcc track notes quiet cut1 short options
input Y Y Y Y Y Y Y -i
output Y Y N Y Y N Y!1 -o,-m,-f
Hz/buf/hop Y Y Y Y Y Y!2 Y -r,-B-,H
jack Y Y N Y Y N!3 N -j
onset Y N N Y!8 Y!6 N Y -O,-t,-M
pitch N Y N N Y!6 N N!5 -p,-u,-l
silence Y Y N Y Y!7 Y N!4 -s
timefmt Y Y Y Y Y Y ! -T
help Y Y Y Y Y Y Y -h
verbose Y Y Y Y Y Y Y -v
  1. aubiocut --output is used to specify a directory, not a file.
  2. Option --bufsize is useless for aubioquiet
  3. aubioquiet could have a jack output
  4. Regression, re-add slicing at silences to aubiocut
  5. aubiocut could cut on notes
  6. aubionotes needs onset/pitch setters.
  7. Silence was different for pitch and onset, test.
  8. Some aubiotrack options should be disabled (minioi, threshold).