Skip to main content

A collection of python scripts for extracting and analyzing acoustics from audio files.

Project description

https://img.shields.io/badge/license-MIT-blue.svg?

A collection of python scripts for extracting and analyzing acoustics from audio files.

1   Common Use Cases

What can you do with this library?

  • Extract pitch and intensity:

    pyacoustics.intensity_and_pitch.praat_pi.getPraatPitchAndIntensity()
    
  • Extract segments of a wav file:

    pyacoustics.signals.audio_scripts.getSubwav()
    
  • Perform simple manipulations on wav files:

    pyacoustics.signals.resampleAudio()
    
    pyacoustics.signals.splitStereoAudio()
    
  • Split audio files on segments of silence or on pure tones:

    pyacoustics.speech_detection.split_on_tone.splitFileOnTone()
    
  • Programmatically manipulate pitch or duration of a file:

    pyacoustics.morph.morph_utils.praat_pitch()
    
  • Mask speech with speech shaped noise:

    pyacoustics.speech_filters.speech_shaped_noise.batchMaskSpeakerData()
    
  • And more!

2   Major revisions

Ver 1.0 (June 7, 2015)

  • first public release.

3   Features as they are added

Mask speech with speech shaped noise (March 21, 2016)

Find syllable nuclei/estimate speech rate using Uwe Reichel’s matlab code (July 29, 2015)

Find the valley bottom between peaks (July 7th, 2015)

4   Requirements

Many of the individual features require different packages. If you aren’t using those packages then you don’t need to install the dependencies.

pyacoustics.intensity_and_pitch.praat_pi requires praat

pyacoustics.intensity_and_pitch.get_f0 requires the ESPS getF0 function as implemented by Snack although I recall having difficulty installing it.

pyacoustics.speech_rate/dictionary_estimate.py requires my library psyle

pyacoustics.signals.data_fitting.py requires SciPy, NumPy, and scikit-learn

My praatIO library is used extensively and can be downloaded here

5   Installation

If you on Windows, you can use the installer found here (check that it is up to date though) Windows installer

PyAcoustics is on pypi and can be installed or upgraded from the command-line shell with pip like so:

python -m pip install pyacoustics --upgrade

Otherwise, to manually install, after downloading the source from github, from a command-line shell, navigate to the directory containing setup.py and type:

python setup.py install

If python is not in your path, you’ll need to enter the full path e.g.:

C:\Python36\python.exe setup.py install

6   Example usage

See the example folders for a few real-world examples using this library.

  • examples/split_audio_on_silence.py

    Detects the presence of speech in a recording based on acoustic intensity. Everything louder than some threshold specified by the user is considered speech.

  • examples/split_audio_on_tone.py

    Detects the presence of pure tones in a recording. One can use this to automatically segment stimuli. Beeps can be played while the speech is being recorded and then later this tool can automatically segment the speech, based on the presence of those tones.

    Also detects speech using a pitch analysis. Most syllables contain some voicing, so a stream of modulating pitch values suggests that someone is speaking. This aspect is not extensively tested but it works well for the example files.

  • examples/estimate_speech_rate.py

    Calculates the speech rate through a matlab script written by Uwe Reichel that estimates the location of syllable boundaries.

7   Citing LMEDS

PyAcoustics is general purpose coding and doesn’t need to be cited but if you would like to, it can be cited like so:

Tim Mahrt. PyAcoustics. https://github.com/timmahrt/pyAcoustics, 2016.

8   Acknowledgements

PyAcoustics is an ongoing collection of code with contributions from a number of projects worked on over several years. Development of various aspects of PyAcoustics was possible thanks to NSF grant IIS 07-03624 to Jennifer Cole and Mark Hasegawa-Johnson, NSF grant BCS 12-51343 to Jennifer Cole, José Hualde, and Caroline Smith, and NSF grant IBSS SMA 14-16791 to Jennifer Cole, Nancy McElwain, and Daniel Berry.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for pyacoustics, version 1.0.3
Filename, size File type Python version Upload date Hashes
Filename, size pyacoustics-1.0.3-py2.py3-none-any.whl (36.8 kB) File type Wheel Python version py2.py3 Upload date Hashes View
Filename, size pyacoustics-1.0.3.tar.gz (27.5 kB) File type Source Python version None Upload date Hashes View

Supported by

Pingdom Pingdom Monitoring Google Google Object Storage and Download Analytics Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page