mlsanityData to 19 Oct 2026

Weak-Supervised Dysarthria-invariant Features for Spoken Language Understanding using an FHVAE and Adversarial Training

arXiv 2210.13144 ↗First posted 24 Oct 2022eess.AS cs.SDcited by 0

On the map: Speech and audio language models → ASR evaluation, bias and atypical speech

Abstract (arXiv)

The scarcity of training data and the large speaker variation in dysarthric speech lead to poor accuracy and poor speaker generalization of spoken language understanding systems for dysarthric speech. Through work on the speech features, we focus on improving the model generalization ability with limited dysarthric data. Factorized Hierarchical Variational Auto-Encoders (FHVAE) trained unsupervisedly have shown their advantage in disentangling content and speaker representations. Earlier work showed that the dysarthria shows in both feature vectors. Here, we add adversarial training to bridge the gap between the control and dysarthric speech data domains. We extract dysarthric and speaker invariant features using weak supervision. The extracted features are evaluated on a Spoken Language Understanding task and yield a higher accuracy on unseen speakers with more severe dysarthria compared to features from the basic FHVAE model or plain filterbanks.

Key facts. No citing papers in the map yet (data through 19 Oct 2026). Placed in ASR evaluation, bias and atypical speech, one of 11 directions in Speech and audio language models. Builds on 19 of its 26 references that are in the map. First posted on arXiv 24 Oct 2022.

Builds on

19 of 26 references.

Closest ancestors · 4

Same direction, newest first

  1. 2022Personalized Adversarial Data Augmentation for Dysarthric and Elderly Speech Recognition13 May
  2. 2021Significance of Data Augmentation for Improving Cleft Lip and Palate Speech Recognition2 Oct
  3. 2021Adversarial Data Augmentation for Disordered Speech Recognition2 Aug
  4. 2021A Study into Pre-training Strategies for Spoken Language Understanding on Dysarthric Speech15 Jun

Other references · 15

  1. 2017Attention Is All You Needcited by 61,180
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,923
  3. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 2,293
  4. 2017Dynamic Routing Between Capsulescited by 692
  5. 2020A Review on Generative Adversarial Networks: Algorithms, Theory, and Applicationscited by 210
  6. 2017Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Datacited by 100
  7. 2019Personalizing ASR for Dysarthric and Accented Speech with Limited Datacited by 58
  8. 2021Residual Adapters for Parameter-Efficient ASR Adaptation to Atypical and Accented Speechcited by 39
  9. 2018Simulating dysarthric speech for training data augmentation in clinical speech applicationscited by 19
  10. 2018Capsule Networks for Low Resource Spoken Language Understandingcited by 13
  11. 2022A Scalable Model Specialization Framework for Training and Inference using Submodels and its Application to Speech Model Personalizationcited by 10
  12. 2018Scalable Factorized Hierarchical Variational Autoencoder Trainingcited by 7
3 more
  1. 2020A light transformer for speech-to-intent applicationscited by 3
  2. 2021Speech Disorder Classification Using Extended Factorized Hierarchical Variational Auto-encoderscited by 3
  3. 2018Unsupervised Representation Learning of Speech for Dialect Identificationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Systematic Study of Dysarthric Speech Recognition: Spectral Features and Acoustic Models
  2. 2024Enhancing Pre-trained ASR System Fine-tuning for Dysarthric Speech Recognition using Adversarial Data Augmentation
  3. 2026Cross-Dataset, Age, and Gender Generalization: A Comprehensive Analysis of Fine-Tuning Strategies for Low-Resource Children's ASR
  4. 2026Differentiable and Severity-invariant Discrete Tokens for Dysarthric Speech Recognition
  5. 2024Speech Recognition-based Feature Extraction for Enhanced Automatic Severity Classification in Dysarthric Speech
  6. 2025Zero- and One-Shot Data Augmentation for Sentence-Level Dysarthric Speech Recognition in Constrained Scenarios
  7. 2025DyPCL: Dynamic Phoneme-level Contrastive Learning for Dysarthric Speech Recognition
  8. 2024Enhancing Dysarthric Speech Recognition for Unseen Speakers via Prototype-Based Adaptation