wSTMI: A speech intelligibility prediction algorithm for noisy and processed speech

Application for perceptual intelligibility rating of dysarthric speech using a visual analog scale (VAS). This app allows users to evaluate intelligibility of speech recordings in their Android phones.

Python library for calculating the mean opinion score and 95% confidence interval of the standard deviation of text-to-speech ratings according to Ribeiro et al. (2011).

This repository contains the supplementary materials for the paper: “Machine Learning Framework for Speech Intelligibility Prediction using Binaural Room Impulse Responses” (Alfian et al., 2026)

Interpretable machine learning algorithm

Python implementation of a few speech intelligibility prediction algorithms

Modified Rhyme Test Speech Intelligibility Graphical User Interface

Random Planted Forest

MATLAB implementation of the Speech Transmission Index for Public Address (STIPA) method for evaluating the speech transmission quality.

A Python implementation of the Speech Intelligibility Index

High-Fidelity Neural Phonetic Posteriorgrams