WSJ

The 'WSJ' dataset is a benchmark for speech recognition that contains transcribed audio data from the Wall Street Journal, used to evaluate the performance of speech recognition systems.

Papers using WSJ (15)

MixRep: Hidden Representation Mixup for Low-Resource Speech Recognition2023 · 5 citesBoosting CTC-Based ASR Using LLM-Based Intermediate Loss Regularization2025 · 1 citesTeaching the Teachers: Boosting unsupervised domain adaptation in speech recognition by ensemble update2026Generative Speech Recognition Error Correction with Large Language Models and Task-Activating Prompting2023 · 46 citesInvestigation of Ensemble features of Self-Supervised Pretrained Models for Automatic Speech Recognition2022 · 16 citesAn Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition2021 · 8 citesMMS-MSG: A Multi-purpose Multi-Speaker Mixture Signal Generator2022 · 7 citesProgressive unsupervised domain adaptation for ASR using ensemble models and multi-stage training2024 · 2 citesTowards Decoupling Frontend Enhancement and Backend Recognition in Monaural Robust ASR2024 · 1 citesAn Investigation of Enhancing CTC Model for Triggered Attention-based Streaming ASR2021Domain Adaptation of low-resource Target-Domain models using well-trained ASR Conformer Models2022Chain-based Discriminative Autoencoders for Speech Recognition2022FeaRLESS: Feature Refinement Loss for Ensembling Self-Supervised Learning Features in Robust End-to-end Speech Recognition2022Minimum Latency Training of Sequence Transducers for Streaming End-to-End Speech Recognition2022Noise-robust Speech Separation with Fast Generative Correction2024