CHiME-4

The CHiME-4 dataset is used to evaluate automatic speech recognition (ASR) systems in noisy environments, containing recordings of speech mixed with various types of background noise.

Papers using CHiME-4 (26)

FlexIO: Flexible Single- and Multi-Channel Speech Separation and Enhancement2025 · 1 citesFrontend Token Enhancement for Token-Based Speech Recognition2026Noisy Disentanglement with Tri-stage Training for Noise-Robust Speech Recognition2025Mixture to Beamformed Mixture: Leveraging Beamformed Mixture as Weak-Supervision for Speech Enhancement and Noise-Robust ASR2025Reducing the Gap Between Pretrained Speech Enhancement and Recognition Models Using a Real Speech-Trained Bridging Module2025ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding2022 · 28 citesSpeaker Reinforcement Using Target Source Extraction for Robust Automatic Speech Recognition2022 · 13 citesWav2vec-Switch: Contrastive Learning from Original-noisy Speech Pairs for Robust Speech Recognition2021 · 7 citesA Conformer Based Acoustic Model for Robust Automatic Speech Recognition2022 · 6 citesClosing the Gap Between Time-Domain Multi-Channel Speech Enhancement on Real and Simulation Conditions2021 · 5 citesMulti-Variant Consistency based Self-supervised Learning for Robust Automatic Speech Recognition2021 · 3 citesRobust Data2vec: Noise-robust Speech Representation Learning for ASR by Combining Regression and Improved Contrastive Learning2022 · 2 citesImproving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstruction2021 · 1 citesDual-Path Style Learning for End-to-End Noise-Robust Speech Recognition2022 · 1 citesEnd-to-End Integration of Speech Recognition, Speech Enhancement, and Self-Supervised Learning Representation2022 · 1 citesExploration of Adapter for Noise Robust Automatic Speech Recognition2024 · 1 citesTowards Decoupling Frontend Enhancement and Backend Recognition in Monaural Robust ASR2024 · 1 citesExploiting Single-Channel Speech For Multi-channel End-to-end Speech Recognition2021Exploiting Single-Channel Speech for Multi-Channel End-to-End Speech Recognition: A Comparative Study2022Multiple-hypothesis RNN-T Loss for Unsupervised Fine-tuning and Self-training of Neural Transducer2022End-to-End Integration of Speech Recognition, Dereverberation, Beamforming, and Self-Supervised Learning Representation2022Gradient Remedy for Multi-Task Learning in End-to-End Noise-Robust Speech Recognition2023Statistical Beamformer Exploiting Non-stationarity and Sparsity with Spatially Constrained ICA for Robust Speech Recognition2023ctPuLSE: Close-Talk, and Pseudo-Label Based Far-Field, Speech Enhancement2024Self-Supervised Learning for Multi-Channel Neural Transducer2024Evolutionary Prompt Design for LLM-Based Post-ASR Error Correction2024