UASpeech

UASpeech is a benchmark dataset that contains dysarthric speech samples used to evaluate the performance of speech recognition systems, particularly in the context of privacy-preserving federated learning for dysarthric and elderly speech recognition.

Papers using UASpeech (2)

Towards Personalized Federated Learning for Dysarthric Speech Recognition2026Regularized Federated Learning for Privacy-Preserving Dysarthric and Elderly Speech Recognition2025