2. General

Download

Type the following in your terminal:

git clone https://github.com/tyiannak/pyAudioAnalysis.git

In order to be able to call the pyAudioAnalysis library from any path you need to add the folder that contains it in the ~/.bashrc file. In particular, add a line as the follow in ~/.bashrc:

export PYTHONPATH=$PYTHONPATH:"/home/bla/bla"

(use the exact path where the pyAudioAnalysis folder is contained - without the pyAudioAnalysis name, e.g. if the library is contained in /home/tyiannak/Research/libraries/pyAudioAnalysis, then use /home/tyiannak/Research/libraries in the bashrc file)

Then, you need to update the path details:

 source ~/.bashrc

Dependencies

Below you can find a list of library dependencies, along with the Linux commands to install them.

• NUMPY

pip install numpy

• MATPLOTLIB

pip install matplotlib

• SCIPY

pip install scipy  

• SKLEARN

pip install sklearn 

• hmmlearn

pip install hmmlearn

• Simplejson

pip install simplejson

• eyeD3

pip install eyed3

• pydub

pip install pydub

General Library Description

The library code is organized in 6 Python files. In particular:

• audioAnalysis.py: this file implements the command-line interface of the basic functionalities of the library, along with some recording functionalities.

• ShortTertFeatures.py: this is where all short-term audio feature extraction is implemented. In total, 21 short-term features are computed, while a mid-term windowing technique is also implemented in another file (see MidTermFeatures.py)

• MidTermFeatures.py: this is where the mid-term windowing technique is implemented, in order to extract statistics of short-term audio features.

• audioTrainTest.py: this file implements the audio classification prodecures. It contains functions that can be used to train a Support Vector Machine or k-Nearest-Neighbour classifier. Also, wrapper functions and scripts are provided for general training, evaluating and feature normalization issues.

• audioSegmentation.py: this file implements audio segmentation functionalities, e.g. fixed-sized segment classification and segmentation, speaker diarization, etc.

• audioBasicIO.py: this file implements some basic audio IO functionalities as well as file convertions

• audioVisualization.py: the purpose of this set of functions is to produce user-friendly and representative content visualizations

In the data/ folder, some audio sample files are provided, while in the data/models subfolders you will find some pretrained SVM and kNN models for particular classification tasks (e.g. Speech vs Music, Musical Genre Classification, etc).