pyAudioProcessing: Audio Processing, Feature Extraction, and Machine Learning Modeling

pyAudioProcessing is a Python based library for processing audio data, constructing and extracting numerical features from audio, building testing machine learning models, classifying data with existing pre-trained classification models or custom user-built models. MATLAB popular language of choice vast amount research in the speech domain. On contrary, remains majority functionality. This contains built that were originally published MATLAB. allows user to compute various files including Gammatone Frequency Cepstral Coefficients (GFCC), Mel (MFCC), spectral features, chroma others such as beat-based cepstrum-based audio. One can use these along one’s own backend any scikit-learn classifiers have been integrated into pyAudioProcessing. Cleaning functions strip unwanted portions are another offering library. It further integrations other functionalities frequency time-series visualizations format conversions. software aims provide engineers, scientists, researchers, students set baseline classify The available at https://github.com/jsingh811/pyAudioProcessing under GPL-3.0 license.