UaSpeech

The 'UaSpeech' dataset is a novel annotated real-world test set of Polish dysarthric speech, curated for evaluating automatic speech recognition (ASR) performance on both natural and synthetic dysarthric speech.

Papers using UaSpeech (35)

An Attention Long Short-term Memory Based System For Automatic Classification Of Speech Intelligibility2024 · 43 citesOn Using The Ua-speech And TORGO Databases To Validate Automatic Dysarthric Speech Classification Approaches2022 · 32 citesOn Combining Acoustic And Modulation Spectrograms In An Attention Lstm-based System For Speech Intelligibility Level Classification2024 · 15 citesSpectro-temporal Deep Features For Disordered Speech Assessment And Recognition2022 · 16 citesExploiting Cross Domain Acoustic-to-articulatory Inverted Features For Disordered Speech Recognition2022 · 12 citesVariational Auto-encoder Based Variability Encoding For Dysarthric Speech Recognition2022 · 8 citesTowards Inclusive ASR: Investigating Voice Conversion for Dysarthric Speech Recognition in Low-Resource Languages2025 · 5 citesColm-dsr: Leveraging Neural Codec Language Modeling For Multi-modal Dysarthric Speech Reconstruction2024 · 2 citesBridging 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 Recognition2025Phone-purity Guided Discrete Tokens for Dysarthric Speech Recognition2025 · 2 citesDuta-vc: A Duration-aware Typical-to-atypical Voice Conversion Approach With Diffusion Probabilistic Model2023 · 22 citesHyper-parameter Adaptation Of Conformer ASR Systems For Elderly And Dysarthric Speech Recognition2023 · 7 citesHomogeneous Speaker Features For On-the-fly Dysarthric And Elderly Speaker Adaptation2024Structured Speaker-deficiency Adaptation Of Foundation Models For Dysarthric And Elderly Speech Recognition2024Enhancing Dysarthria Speech Feature Representation With Empirical Mode Decomposition And Walsh-hadamard Transform2023Adversarial 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 citesSpeech 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 Recognition2024An 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