Stars
SCOREQ: Speech COntrastive REgression for Quality Assessment (NeurIPS 2024)
A video quality MOS prediction model for videoconferencing calls that takes temporal distortions into account
Repository for Reinforcement learning based bandwidth estimation challenge
Open source reference implementation of ITU-T P.1204.3
Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters
Self-Supervised Speech Pre-training and Representation Learning Toolkit
A Python library for audio data augmentation. Useful for making audio ML models work well in the real world, not just in the lab.
AQP is a modular pipeline built to enable the comparison and testing of different quality metric configurations.
Tutorials, assignments, and competitions for MIT Deep Learning related courses.
Bias-Aware Loss for Training Image and Speech Quality Prediction Models from Multiple Dataset
Tips for releasing research code in Machine Learning (with official NeurIPS 2020 recommendations)
MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement (ICML 2019, with Travel awards)
An open-source framework for modeling real-time conversations in spoken dialogue systems.
💎 A list of accessible speech corpora for ASR, TTS, and other Speech Technologies
🔊 A comprehensive list of open-source datasets for voice and sound computing (95+ datasets).
A wrapper around speech quality metrics MOSNet, BSSEval, STOI, PESQ, SRMR, SISDR
babaknaderi / P.835
Forked from microsoft/P.808This is an open-source implementation of the ITU P.808 standard for "Subjective evaluation of speech quality with a crowdsourcing approach" (see https://www.itu.int/rec/T-REC-P.808/en). It uses Ama…
Subjective quality scores recovery from noisy measurements.
Latex code for making neural networks diagrams
Deep Learning based Quality metric for gaming content
Implementation of "MOSNet: Deep Learning based Objective Assessment for Voice Conversion"
Reference Implementations of Waveform Evaluation Networks (WEnets)
NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment
This is an open-source implementation of the ITU P.808 standard for "Subjective evaluation of speech quality with a crowdsourcing approach" (see https://www.itu.int/rec/T-REC-P.808/en). It uses Ama…