mlsanityData to 7 Oct 2026

Investigation of Data Augmentation Techniques for Disordered Speech Recognition

arXiv 2201.05562 ↗First posted 14 Jan 2022cs.SD cs.AI cs.LGcited by 27

Not on the map. Why?

Abstract (arXiv)

Disordered speech recognition is a highly challenging task. The underlying neuro-motor conditions of people with speech disorders, often compounded with co-occurring physical disabilities, lead to the difficulty in collecting large quantities of speech required for system development. This paper investigates a set of data augmentation techniques for disordered speech recognition, including vocal tract length perturbation (VTLP), tempo perturbation and speed perturbation. Both normal and disordered speech were exploited in the augmentation process. Variability among impaired speakers in both the original and augmented data was modeled using learning hidden unit contributions (LHUC) based speaker adaptive training. The final speaker adapted system constructed using the UASpeech corpus and the best augmentation approach based on speed perturbation produced up to 2.92% absolute (9.3% relative) word error rate (WER) reduction over the baseline system without data augmentation, and gave an overall WER of 26.37% on the test set containing 16 dysarthric speakers.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 9 of its 45 references that are in the map. First posted on arXiv 14 Jan 2022.

Builds on

9 of 45 references.

References · 9

  1. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  2. 2019RWTH ASR Systems for LibriSpeech: Hybrid vs Attention -- w/o Data Augmentationcited by 63
  3. 2013Deep Scattering Spectrumcited by 52
  4. 2017The Microsoft 2017 Conversational Speech Recognition Systemcited by 51
  5. 2017English Conversational Telephone Speech Recognition by Humans and Machinescited by 40
  6. 2016Learning Hidden Unit Contributions for Unsupervised Acoustic Model Adaptationcited by 38
  7. 2018Back-Translation-Style Data Augmentation for End-to-End ASRcited by 28
  8. 2018Simulating dysarthric speech for training data augmentation in clinical speech applicationscited by 14
  9. 2019English Broadcast News Speech Recognition by Humans and Machinescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 9; 2023: 8; 2024: 3; 2025: 3; 2026: 4.

27 papers.

Sort:

By area:

  1. 2022SpeechSplit 2.0: Unsupervised speech disentanglement for voice conversion Without tuning autoencoder Bottleneckscited by 27
  2. 2022Speaker Adaptation Using Spectro-Temporal Deep Features for Dysarthric and Elderly Speech Recognitioncited by 19
  3. 2022Recent Progress in the CUHK Dysarthric Speech Recognition Systemcited by 17
  4. 2022Personalized Adversarial Data Augmentation for Dysarthric and Elderly Speech Recognitioncited by 16
  5. 2023Exploring Self-supervised Pre-trained ASR Models For Dysarthric and Elderly Speech Recognitioncited by 14
  6. 2022Conformer Based Elderly Speech Recognition System for Alzheimer's Disease Detectioncited by 12
  7. 2022Exploiting Cross Domain Acoustic-to-articulatory Inverted Features For Disordered Speech Recognitioncited by 9
  8. 2024Self-supervised ASR Models and Features For Dysarthric and Elderly Speech Recognitioncited by 9
  9. 2022Cross-lingual Dysarthria Severity Classification for English, Korean, and Tamilcited by 8
  10. 2023Use of Speech Impairment Severity for Dysarthric Speech Recognitioncited by 8
  11. 2022Exploiting Cross-domain And Cross-Lingual Ultrasound Tongue Imaging Features For Elderly And Dysarthric Speech Recognitioncited by 7
  12. 2023Accurate synthesis of Dysarthric Speech for ASR data augmentationcited by 7
15 more
  1. 2023DuTa-VC: A Duration-aware Typical-to-atypical Voice Conversion Approach with Diffusion Probabilistic Modelcited by 6
  2. 2022On-the-Fly Feature Based Rapid Speaker Adaptation for Dysarthric and Elderly Speech Recognitioncited by 5
  3. 2023Hyper-parameter Adaptation of Conformer ASR Systems for Elderly and Dysarthric Speech Recognitioncited by 4
  4. 2023No Pitch Left Behind: Addressing Gender Unbalance in Automatic Speech Recognition through Pitch Manipulationcited by 4
  5. 2023Debiased Automatic Speech Recognition for Dysarthric Speech via Sample Reweighting with Sample Affinity Testcited by 3
  6. 2025Towards Inclusive ASR: Investigating Voice Conversion for Dysarthric Speech Recognition in Low-Resource Languagescited by 3
  7. 2024Homogeneous Speaker Features for On-the-Fly Dysarthric and Elderly Speaker Adaptationcited by 2
  8. 2024Not All Errors Are Equal: Investigation of Speech Recognition Errors in Alzheimer's Disease Detectioncited by 2
  9. 2025Fairness in Dysarthric Speech Synthesis: Understanding Intrinsic Bias in Dysarthric Speech Cloning using F5-TTScited by 1
  10. 2023Arabic Dysarthric Speech Recognition Using Adversarial and Signal-Based Augmentationcited by 0
  11. 2025On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognitioncited by 0
  12. 2026Controllable Dysarthric Speech Synthesis with Patient-Specific Conditioning for Speaker-Diverse ASR Augmentationcited by 0
  13. 2026Huntington Disease Automatic Speech Recognition with Biomarker Supervisioncited by 0
  14. 2026Towards Personalized Federated Learning for Dysarthric Speech Recognitioncited by 0
  15. 2026Augmenting Dysarthric Speech Severity Assessment with MOS Supervisioncited by 0