mlsanityData to 14 Oct 2026

Hyper-parameter Adaptation of Conformer ASR Systems for Elderly and Dysarthric Speech Recognition

arXiv 2306.15265 ↗First posted 27 Jun 2023eess.AS cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Automatic recognition of disordered and elderly speech remains highly challenging tasks to date due to data scarcity. Parameter fine-tuning is often used to exploit the large quantities of non-aged and healthy speech pre-trained models, while neural architecture hyper-parameters are set using expert knowledge and remain unchanged. This paper investigates hyper-parameter adaptation for Conformer ASR systems that are pre-trained on the Librispeech corpus before being domain adapted to the DementiaBank elderly and UASpeech dysarthric speech datasets. Experimental results suggest that hyper-parameter adaptation produced word error rate (WER) reductions of 0.45% and 0.67% over parameter-only fine-tuning on DBank and UASpeech tasks respectively. An intuitive correlation is found between the performance improvements by hyper-parameter domain adaptation and the relative utterance length ratio between the source and target domain data.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 23 of its 43 references that are in the map. First posted on arXiv 27 Jun 2023.

Builds on

23 of 43 references.

References · 23

  1. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  2. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  3. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 558
  4. 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 414
  5. 2018SNAS: Stochastic Neural Architecture Searchcited by 289
  6. 2020Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognitioncited by 187
  7. 2021Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Trainingcited by 151
  8. 2020Recent Developments on ESPnet Toolkit Boosted by Conformercited by 132
  9. 2021WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkitcited by 125
  10. 2021BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognitioncited by 88
  11. 2021SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Networkcited by 83
  12. 2020DSNAS: Direct Neural Architecture Search without Parameter Retrainingcited by 69
11 more
  1. 2019Personalizing ASR for Dysarthric and Accented Speech with Limited Datacited by 45
  2. 2020Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognitioncited by 39
  3. 2022Investigation of Data Augmentation Techniques for Disordered Speech Recognitioncited by 27
  4. 2022Speaker Adaptation Using Spectro-Temporal Deep Features for Dysarthric and Elderly Speech Recognitioncited by 19
  5. 2020Improved End-to-End Dysarthric Speech Recognition via Meta-learning Based Model Re-initializationcited by 17
  6. 2022Recent Progress in the CUHK Dysarthric Speech Recognition Systemcited by 17
  7. 2020DARTS-ASR: Differentiable Architecture Search for Multilingual Speech Recognition and Adaptationcited by 15
  8. 2022Spectro-Temporal Deep Features for Disordered Speech Assessment and Recognitioncited by 13
  9. 2022Conformer Based Elderly Speech Recognition System for Alzheimer's Disease Detectioncited by 12
  10. 2022Neural Architecture Search For LF-MMI Trained Time Delay Neural Networkscited by 11
  11. 2021Darts-Conformer: Towards Efficient Gradient-Based Neural Architecture Search For End-to-End ASRcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 1; 2026: 1.

4 papers.

  1. 2024Self-supervised ASR Models and Features For Dysarthric and Elderly Speech Recognitioncited by 9
  2. 2024Enhancing Dysarthric Speech Recognition for Unseen Speakers via Prototype-Based Adaptationcited by 4
  3. 2025DyPCL: Dynamic Phoneme-level Contrastive Learning for Dysarthric Speech Recognitioncited by 2
  4. 2026Augmenting Dysarthric Speech Severity Assessment with MOS Supervisioncited by 0