UA-Speech

The UA-Speech dataset is a collection of multi-speaker non-normative speech data used to evaluate the effectiveness of adaptation methods for automatic speech recognition systems in recognizing atypical speech patterns.

Papers using UA-Speech (30)

Towards Inclusive ASR: Investigating Voice Conversion for Dysarthric Speech Recognition in Low-Resource Languages2025 · 5 citesPhone-purity Guided Discrete Tokens for Dysarthric Speech Recognition2025 · 2 citesTowards Personalized Federated Learning for Dysarthric Speech Recognition2026Bridging the Reality Gap in ASR for Low-Resource Dysarthric Speech: Evaluating Performance on Synthetic and Real Data2026End-to-End Simultaneous Dysarthric Speech Reconstruction with Frame-Level Adaptor and Multiple Wait-k Knowledge Distillation2026Two-Stage Adaptation for Non-Normative Speech Recognition: Revisiting Speaker-Independent Initialization for Personalization2026Enhancing Speaker-Independent Dysarthric Speech Severity Classification with DSSCNet and Cross-Corpus Adaptation2025DiffDSR: Dysarthric Speech Reconstruction Using Latent Diffusion Model2025On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition2025Enhancing Dysarthria Speech Feature Representation With Empirical Mode Decomposition And Walsh-hadamard Transform2023Personalized Adversarial Data Augmentation for Dysarthric and Elderly Speech Recognition2022 · 3 citesAdversarial Data Augmentation Using VAE-GAN for Disordered Speech Recognition2022 · 1 citesOn using the UA-Speech and TORGO databases to validate automatic dysarthric speech classification approaches2022 · 1 citesDuTa-VC: A Duration-aware Typical-to-atypical Voice Conversion Approach with Diffusion Probabilistic Model2023 · 1 citesEnhancing Pre-trained ASR System Fine-tuning for Dysarthric Speech Recognition using Adversarial Data Augmentation2024 · 1 citesCoLM-DSR: Leveraging Neural Codec Language Modeling for Multi-Modal Dysarthric Speech Reconstruction2024 · 1 citesSpeaker Adaptation Using Spectro-Temporal Deep Features for Dysarthric and Elderly Speech Recognition2022On-the-Fly Feature Based Rapid Speaker Adaptation for Dysarthric and Elderly Speech Recognition2022Speaker adaptation for Wav2vec2 based dysarthric ASR2022Speech Intelligibility Classifiers from 550k Disordered Speech Samples2023Use of Speech Impairment Severity for Dysarthric Speech Recognition2023Hyper-parameter Adaptation of Conformer ASR Systems for Elderly and Dysarthric Speech Recognition2023Towards Automatic Data Augmentation for Disordered Speech Recognition2023UNIT-DSR: Dysarthric Speech Reconstruction System Using Speech Unit Normalization2024Homogeneous Speaker Features for On-the-Fly Dysarthric and Elderly Speaker Adaptation2024Self-supervised ASR Models and Features For Dysarthric and Elderly Speech Recognition2024Structured Speaker-Deficiency Adaptation of Foundation Models for Dysarthric and Elderly Speech Recognition2024Spectro-Temporal Deep Features for Disordered Speech Assessment and Recognition2022An Attention Long Short-Term Memory based system for automatic classification of speech intelligibility2024On combining acoustic and modulation spectrograms in an attention LSTM-based system for speech intelligibility level classification2024