TORGO

The TORGO dataset is a benchmark that contains recordings of dysarthric speech used to evaluate the effectiveness of automatic speech recognition (ASR) systems in recognizing and processing speech with abnormal prosody and significant speaker variability.

Papers using TORGO (16)

Confidence-Guided Error Correction for Disordered Speech Recognition2025 · 1 citesTowards Personalized Federated Learning for Dysarthric Speech Recognition2026DARS: Dysarthria-Aware Rhythm-Style Synthesis for ASR Enhancement2026Prototype-Based Disentanglement for Controllable Dysarthric Speech Synthesis2026Enhancing Speaker-Independent Dysarthric Speech Severity Classification with DSSCNet and Cross-Corpus Adaptation2025Fairness in Dysarthric Speech Synthesis: Understanding Intrinsic Bias in Dysarthric Speech Cloning using F5-TTS2025Dysarthria Normalization via Local Lie Group Transformations for Robust ASR2025Enhancing Dysarthria Speech Feature Representation With Empirical Mode Decomposition And Walsh-hadamard Transform2023Personalized Adversarial Data Augmentation for Dysarthric and Elderly Speech Recognition2022 · 3 citesAccurate synthesis of Dysarthric Speech for ASR data augmentation2023 · 2 citesFew-Shot Speaker Identification Using Depthwise Separable Convolutional Network with Channel Attention2022 · 1 citesOn using the UA-Speech and TORGO databases to validate automatic dysarthric speech classification approaches2022 · 1 citesSpeaker Adaptation Using Spectro-Temporal Deep Features for Dysarthric and Elderly Speech Recognition2022Speech Intelligibility Classifiers from 550k Disordered Speech Samples2023Homogeneous Speaker Features for On-the-Fly Dysarthric and Elderly Speaker Adaptation2024Self-supervised ASR Models and Features For Dysarthric and Elderly Speech Recognition2024