---
id: pystoi
version: "0.4.1"
license: MIT
license_treatment: permissive
maintenance: dormant
---

# pystoi — Computes Short Term Objective Intelligibility measure

License: permissive · Maintenance: dormant · Downloads: 922.0K/mo

## What it is and what it does

pystoi is a Python implementation of the classical and extended Short Term Objective Intelligibility (STOI) measures, which quantify how intelligible a degraded speech signal is relative to a clean reference. It takes two audio signals—one clean and one degraded by noise, processing, or vocoding—and returns a score correlating with perceived intelligibility. The package wraps numpy and scipy to perform the time-frequency analysis underlying the STOI algorithm.

The measure is intrusive (requires both signals) and serves as an alternative to speech intelligibility index (SII) or speech transmission index (STI), particularly useful when evaluating nonlinear processing like noise reduction or binary masking. It was ported from Cees Taal's original Matlab implementation and includes both classical and extended variants.

Use it for:

- Evaluate speech quality after noise reduction or denoising algorithms to quantify intelligibility improvement.
- Assess vocoded speech quality in cochlear implant (CI) simulations or other speech coding scenarios.
- Compare intelligibility across different audio processing pipelines or parameter settings.
- Validate speech enhancement systems by measuring intelligibility gain on degraded signals.
- Research speech processing effects on intelligibility in academic or industrial audio labs.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Computes Short Term Objective Intelligibility (STOI) measures for speech signals, quantifying how intelligible degraded audio is compared to a clean reference.

Yes, if you need an intrusive intelligibility metric for speech signals and can accept dormant maintenance. The package is stable, has low install friction, carries no security vulnerabilities, and is MIT-licensed. However, verify compatibility with your Python version and confirm the codebase meets your performance needs, since the last release was 959 days ago.

## Install

pip install pystoi
uv add pystoi
poetry add pystoi

## Installing pystoi

Before you install: Low friction installation with only numpy and scipy as dependencies. Dormant maintenance status—last release was 959 days ago, though the repository remains active and unarchived with 360 stars.

License in practice: MIT license permits commercial and private use with minimal restrictions; attribution required but no copyleft obligations.

Quickstart:

pip install pystoi

from pystoi import stoi
import numpy as np

# clean and degraded are 1D numpy arrays, fs is sample rate
score = stoi(clean, degraded, fs, extended=False)

Input signals must be 1D arrays of equal length; STOI is intrusive (requires both clean reference and degraded signal).

Verify before relying:

- Whether the package works reliably with modern Python 3.x versions (classifiers list both Python 2.7 and 3, but maintenance is dormant).
- Current performance characteristics and whether the 4x speed-up mentioned in the description has been merged into the main branch.

## Package facts

- License: MIT (permissive)
- Python support: unspecified
- Install friction: low
- Maintenance: dormant
- Downloads: 922.0K/month (top 5,000 on PyPI)
- Known vulnerabilities: none known

## Tags

speech intelligibility measurement, STOI audio quality metric, speech degradation assessment, noise reduction evaluation, speech signal comparison, audio intelligibility scoring, vocoded speech quality, speech-processing, audio-quality, signal-analysis

[View on SkillFed](https://skillfed.io/packages/pystoi) · [View on PyPI](https://pypi.org/project/pystoi/)