mlsanityData to 7 Oct 2026

Personalized Automatic Speech Recognition Trained on Small Disordered Speech Datasets

arXiv 2110.04612 ↗First posted 9 Oct 2021eess.AS cs.CL cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

This study investigates the performance of personalized automatic speech recognition (ASR) for recognizing disordered speech using small amounts of per-speaker adaptation data. We trained personalized models for 195 individuals with different types and severities of speech impairment with training sets ranging in size from <1 minute to 18-20 minutes of speech data. Word error rate (WER) thresholds were selected to determine Success Percentage (the percentage of personalized models reaching the target WER) in different application scenarios. For the home automation scenario, 79% of speakers reached the target WER with 18-20 minutes of speech; but even with only 3-4 minutes of speech, 63% of speakers reached the target WER. Further evaluation found similar improvement on test sets with conversational and out-of-domain, unprompted phrases. Our results demonstrate that with only a few minutes of recordings, individuals with disordered speech could benefit from personalized ASR.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 9 of its 17 references that are in the map. First posted on arXiv 9 Oct 2021.

Builds on

9 of 17 references.

References · 9

  1. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  2. 2013Speech Recognition with Deep Recurrent Neural Networkscited by 666
  3. 2018Streaming End-to-end Speech Recognition For Mobile Devicescited by 230
  4. 2020A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latencycited by 99
  5. 2019Recognizing long-form speech using streaming end-to-end modelscited by 77
  6. 2019Personalizing ASR for Dysarthric and Accented Speech with Limited Datacited by 45
  7. 2019Parrotron: An End-to-End Speech-to-Speech Conversion Model and its Applications to Hearing-Impaired Speech and Speech Separationcited by 22
  8. 2020Multi-Accent Adaptation based on Gate Mechanismcited by 9
  9. 2021On-Device Personalization of Automatic Speech Recognition Models for Disordered Speechcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 4; 2024: 4; 2025: 2; 2026: 2.

14 papers.

Sort:

  1. 2024Lost in Transcription: Identifying and Quantifying the Accuracy Biases of Automatic Speech Recognition Systems Against Disfluent Speechcited by 15
  2. 2023Exploring Self-supervised Pre-trained ASR Models For Dysarthric and Elderly Speech Recognitioncited by 14
  3. 2023Text is All You Need: Personalizing ASR Models using Controllable Speech Synthesiscited by 9
  4. 2024Self-supervised ASR Models and Features For Dysarthric and Elderly Speech Recognitioncited by 9
  5. 2022Assessing ASR Model Quality on Disordered Speech using BERTScorecited by 8
  6. 2023Use of Speech Impairment Severity for Dysarthric Speech Recognitioncited by 8
  7. 2022An analysis of degenerating speech due to progressive dysarthria on ASR performancecited by 6
  8. 2024Inclusive ASR for Disfluent Speech: Cascaded Large-Scale Self-Supervised Learning with Targeted Fine-Tuning and Data Augmentationcited by 5
  9. 2023Latent Phrase Matching for Dysarthric Speechcited by 2
  10. 2024Homogeneous Speaker Features for On-the-Fly Dysarthric and Elderly Speaker Adaptationcited by 2
  11. 2025EvolveCaptions: Empowering DHH Users Through Real-Time Collaborative Captioningcited by 0
  12. 2025On the Difficulty of Token-Level Modeling of Dysfluency and Fluency Shaping Artifactscited by 0
2 more
  1. 2026Comparing Human and Automatic Recognition of Dutch Dysarthric Continuous Speech: A Case Studycited by 0
  2. 2026Choosing a PEFT Variant for Per-Patient Dysarthric ASR: A Single-Speaker Case Study on Two ASR Basescited by 0