CHiME-3

CHiME-3 is a dataset that contains recordings of speech mixed with background noise at various signal-to-noise ratios, used to evaluate speech quality assessment systems.

Papers using CHiME-3 (14)

AMDM-SE: Attention-based Multichannel Diffusion Model for Speech Enhancement2026JSQA: Speech Quality Assessment with Perceptually-Inspired Contrastive Pretraining Based on JND Audio Pairs2025Mel-McNet: A Mel-Scale Framework for Online Multichannel Speech Enhancement2025Leveraging Joint Spectral and Spatial Learning with MAMBA for Multichannel Speech Enhancement2024Improving Speech Recognition on Noisy Speech via Speech Enhancement with Multi-Discriminators CycleGAN2021 · 8 citesDereverberation of Autoregressive Envelopes for Far-field Speech Recognition2021 · 1 citesIs the Ideal Ratio Mask Really the Best? -- Exploring the Best Extraction Performance and Optimal Mask of Mask-based Beamformers2023Attention-Driven Multichannel Speech Enhancement in Moving Sound Source Scenarios2023Array Geometry-Robust Attention-Based Neural Beamformer for Moving Speakers2024MC-SEMamba: A Simple Multi-channel Extension of SEMamba2024Similarity-and-Independence-Aware Beamformer with Iterative Casting and Boost Start for Target Source Extraction Using Reference2021Multimodal Audio-Visual Information Fusion using Canonical-Correlated Graph Neural Network for Energy-Efficient Speech Enhancement2022On monoaural speech enhancement for automatic recognition of real noisy speech using mixture invariant training2022RelUNet: Relative Channel Fusion U-Net for Multichannel Speech Enhancement2024