speech-quality

NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment

Python implementation of performance metrics in Loizou's Speech Enhancement book

VoIP signaling and media test automation

A toolkit to calculate speech audio quality. Not affiliated with the original authors

A Python library for computing the Mel-Cepstral Distance (Mel-Cepstral Distortion, MCD) between two inputs. This implementation is based on the method proposed by Robert F. Kubichek in "Mel-Cepstral Distance Measure for Objective Speech Quality Assessment".

Generate degraded speech datasets for noise-robust ASR benchmarking

Research toolkit for evaluating audio steganography and watermarking: payload recovery, signal quality, robustness, capacity and empirical detectability under a shared experimental protocol. Includes a Python API, declarative experiments and a browser-based research interface.

Deep Noise Suppression for Real Time Speech Enhancement in a Single Channel Wide Band Scenario

Objective measures of speech quality SNR

Train no-reference speech quality estimators with multiple datasets via learned, per-dataset alignments.

Go baresip wrapper for automated SIP tests

Python implementation of a few speech intelligibility prediction algorithms

Bias-Aware Loss for Training Image and Speech Quality Prediction Models from Multiple Dataset

A pure Python implementation of Google's ViSQOL (Virtual Speech Quality Objective Listener) for objective audio/speech quality assessment.

This repository belongs to my Bachelor's thesis on predicting voice likability from pre-trained speech embeddings.

Know the quality of your speech

PyTorch-free JAX inference for NISQA speech quality assessment, with bundled verified weights and tested CPU/CUDA support.

Dataset of crowdsourced Speech Quality Assessment using the Comparison Category Rating (CCR) test method

Optimized PyTorch inference for NISQA speech quality and TTS naturalness models

Performance of Objective Speech Quality Metrics on Languages Beyond Validation Data