pystoi
Python implementation of the Short-Time Objective Intelligibility (STOI) measure for speech quality assessment.
What is pystoi?
PySTOI is a Python library that implements the Short-Time Objective Intelligibility (STOI) measure, a standardized algorithm for assessing how understandable processed or degraded speech signals are. It compares clean reference audio with processed versions (e.g., after noise reduction or compression) to predict speech intelligibility scores. The library provides both classical and extended STOI implementations for research and practical applications in speech processing.
Researchers and engineers working in speech processing, audio enhancement, hearing aid development, or communication systems who need to objectively evaluate speech intelligibility. It's particularly useful for those assessing noise reduction algorithms, binary masking techniques, or vocoded speech simulations.
PySTOI offers a well-tested, open-source Python implementation of the widely-used STOI measure, eliminating dependency on proprietary MATLAB code. It provides high correlation with human intelligibility ratings and serves as a modern alternative to traditional measures like SII or STI when evaluating nonlinear speech processing effects.
Overview
Python implementation of the Short Term Objective Intelligibility measure
Use Cases
Best For
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
