noise-robust

Matlab and Python libraries for an unsupervised method for robust voice activity detection (rVAD), as in the paper rVAD: An Unsupervised Segment-Based Robust Voice Activity Detection Method.

The codebase for Data-driven general-purpose voice activity detection.

[EMNLP 2021] Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training

Python port of the Unidip clustering algorithm from: http://www.kdd.org/kdd2016/subtopic/view/skinny-dip-clustering-in-a-sea-of-noise

Unsupervised Voice Activity Detection by Modeling Source and System Information using Zero Frequency Filtering

ICLR 2021: Noise against noise: stochastic label noise helps combat inherent label noise

[CVPR 2025] Official Pytorch implementation of "Learning with Noisy Triplet Correspondence for Composed Image Retrieval".

Lightweight, explainable VAD that beats Silero and WebRTC on noisy audio. No GPU required.

The official respository for noise-aware physics-informed machine learning (nPIML)

SPEAR-ASR and SPEAR-WakeUp Software Development Kit for Android

SPEAR-ASR and SPEAR-WakeUp Software Development Kit in Python for Linux

面向噪声场景的视听语音理解框架：唇音融合 AV-ASR、说话人分离与声学事件理解（纯 NumPy 核心，可选 PyTorch）

Fault-tolerant cockpit audio transcription with MFCC feature extraction, ML classification, and high-noise speech modeling

Depth peeling for point clouds.

SPEAR-ASR and SPEAR-WakeUp Software Development Kit in Java for Windows

SNR-driven adaptive step-size control for CMA-ES under noisy black-box optimization. A transparent proxy layer that adjusts sigma using signal-to-noise ratio estimates, with full experimental infrastructure and sensitivity analysis.

SPEAR-ASR and SPEAR-WakeUp Software Development Kit in Java for Linux

Cross-corpus and noise-robust speech emotion recognition using a lightweight 1D CNN across RAVDESS, CREMA-D, TESS, and SAVEE.