Automatic Speech Recognition of Conversational Speech in Individuals With Disordered Speech
Open accessThe DOI matches its Crossref record; 28 of the 28 references it cites were found in a registry or an index.
Abstract
Purpose: This study examines the effectiveness of automatic speech recognition (ASR) for individuals with speech disorders, addressing the gap in performance between read and conversational ASR. We analyze the factors influencing this disparity and the effect of speech mode–specific training on ASR accuracy. Method: Recordings of read and conversational speech from 27 individuals with various speech disorders were analyzed using both (a) one speaker-independent ASR system trained and optimized for typical speech and (b) multiple ASR models that were personalized to the speech of the participants with disordered speech. Word error rates were calculated for each speech model, read versus conversational, and subject. Linear mixed-effects models were used to assess the impact of speech mode and disorder severity on ASR accuracy. We investigated nine variables, classified as technical, linguistic, or speech impairment factors, for their potential influence on the performance gap. Results: We found a significant performance gap between read and conversational speech in both personalized and unadapted ASR models. Speech impairment severity notably impacted recognition accuracy in unadapted models for both speech modes and in personalized models for read speech. Linguistic attributes of utterances were the most influential on accuracy, though atypical speech characteristics also played a role. Including conversational speech samples in model training notably improved recognition accuracy. Conclusions: We observed a significant performance gap in ASR accuracy between read and conversational speech for individuals with speech disorders. This gap was largely due to the linguistic complexity and unique characteristics of speech disorders in conversational speech. Training personalized ASR models using conversational speech significantly improved recognition accuracy, demonstrating the importance of domain-specific training and highlighting the need for further research into ASR systems capable of handling disordered conversational speech effectively.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures




Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“These considerations align with broader observations that generic recognizers struggle with dysarthric speech, while speaker-specific adaptation consistently narrows the gap (20), a pattern that further motivates expanding personalized ASR evaluations to more heterogeneous listener and speaker populations.”
From Case Report: Tailored automatic speech recognition in global aphasia with dysarthria - a single case proof of concept (2026) · cites this paper as [20]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“For training, we employed the Adam optimizer (Kingma & Ba, 2015) with a low learning rate of 1e-5.”
A guideline of selecting and reporting intraclass correlation coefficients for reliability research
Koo, T. K., & Li, M. Y. (2016) · Journal of Chiropractic Medicine · doi:10.1016/j.jcm.2016.02.012 · Cited by 31,709 · cited 1×
“The results indicated that while most of the labels exhibited good to moderate agreement, the “ Consistency ” label demonstrated poor reliability (Koo & Li, 2016).”
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
Park, D. S., Chan, W., Zhang, Y., Chiu, C.-C., Zoph, B., Cubuk, E. D., & Le, Q. V. (2019) · Interspeech 2019 · doi:10.21437/interspeech.2019-2680 · Cited by 3,558
Supervised Sequence Labelling with Recurrent Neural Networks
Graves, A. (2012) · Studies in Computational Intelligence · doi:10.1007/978-3-642-24797-2 · Cited by 3,120
Robust Speech Recognition via Large-Scale Weak Supervision
Radford, A., Kim, J. W., Xu, T., Brockman, G., McLeavey, C., & Sutskever, I. (2022) · arXiv · doi:10.48550/arxiv.2212.04356 · Cited by 1,953 · cited 1×
“…recognize untranscribed speech recordings of individuals with speech disorders with a reasonable degree of accuracy would allow researchers to utilize a vast amount of pseudolabeled speech recordings for semisupervised speaker-independent model training (Liao et al., 2013; Radford et al., 2023).”
The TORGO database of acoustic and articulatory speech from speakers with dysarthria
Rudzicz, F., Namasivayam, A. K., & Wolff, T. (2012) · Language Resources and Evaluation · doi:10.1007/s10579-011-9145-0 · Cited by 425 · cited 1×
“Most speech disorder corpora focus on speech that is produced during reading, with scant examples of spontaneous conversation (H. Kim et al., 2008; Rudzicz et al., 2012).”
Dysarthric speech database for universal access research
Kim, H., Hasegawa-Johnson, M., Perlman, A., Gunderson, J., Huang, T. S., Watkin, K., & Frame, S. (2008) · Interspeech 2008 · doi:10.21437/interspeech.2008-480 · Cited by 397 · cited 1×
“Most speech disorder corpora focus on speech that is produced during reading, with scant examples of spontaneous conversation (H. Kim et al., 2008; Rudzicz et al., 2012).”
Graves, A. (2012) · Studies in Computational Intelligence · doi:10.1007/978-3-642-24797-2_3 · Cited by 265
Between-speaker and within-speaker variation in speech tempo of American English
Jacewicz, E., Fox, R. A., & Wei, L. (2010) · The Journal of the Acoustical Society of America · doi:10.1121/1.3459842 · Cited by 196 · cited 2×
“…speech presents unique ASR challenges due to its distinct characteristics, such as less precise and faster articulation (DiCanio et al., 2015; Jacewicz et al., 2010; Kuo & Weismer, 2016), and the presence of irregularities such as interruptions, hesitations, repairs, and nonlexical sounds…”
Liao, H., McDermott, E., & Senior, A. (2013) · 2013 IEEE Workshop on Automatic Speech Recognition and Understanding · doi:10.1109/asru.2013.6707758 · Cited by 193 · cited 1×
“…recognize untranscribed speech recordings of individuals with speech disorders with a reasonable degree of accuracy would allow researchers to utilize a vast amount of pseudolabeled speech recordings for semisupervised speaker-independent model training (Liao et al., 2013; Radford et al., 2023).”
Cited by
Transforming Speech-Language Pathology with AI: Opportunities, Challenges, and Ethical Guidelines
Georgiou, G. P. (2025) · Healthcare · doi:10.3390/healthcare13192460 · Cited by 36
“Evidence shows that adapting models to conversational speech from individuals with speech-language disorders improves recognition performance [10].”
Artificial Intelligence in Communication Sciences and Disorders: Introduction to the Forum
Green, J. R. (2024) · Journal of Speech Language and Hearing Research · doi:10.1044/2024_jslhr-24-00594 · Cited by 25
Self-citationHe, Y., Seng, K. P., & Ang, L.-M. (2025) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2025.3570383 · Cited by 22
“Tobin et al. [5] achieved modest WER improvements using domain-specific adaptations, but encountered limitations with severe prosodic disorders due to their reliance on pre-existing datasets.”
Variational Low-Rank Adaptation for Personalized Impaired Speech Recognition
Pokel, N., Moure, P., Boehringer, R., Liu, S., & Gao, Y. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462593 · Cited by 6
Towards a Single ASR Model That Generalizes to Disordered Speech
Tobin, J., Tomanek, K., & Venugopalan, S. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888895 · Cited by 10
“More details of the test set can be found in [18].”
Self-citation
Metadata
- Authors
- Tobin, J., Nelson, P., MacDonald, B., Heywood, R., Cave, R., Seaver, K., Desjardins, A., Jiang, P.-P., & Green, J. R.
- Affiliations
- Google (United States) (US)
- Motor Neurone Disease Association (GB)
- MGH Institute of Health Professions (US)
- Harvard University (US)
- Corresponding author
- Tobin, Jimmy
- ORCID
- Venue
- Journal of Speech, Language, and Hearing Research
- Published
- 2024-11-07
- Volume
- 67
- Issue
- 11
- Pages
- 4176-4185
- ISSN
- 1092-4388 (ISSN-L)
- 1558-9102
- PMC
- PMC12379580
- OpenAlex
- W4400316434
- Cited by
- 45
- References
- 26
- Citations by year
- 2026: 32 · 2025: 11 · 2024: 2
- FWCI
- 6.60
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Journal of Speech Language and Hearing Research (publishedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Funders
- National Institutes of Health
- National Institute on Deafness and Other Communication Disorders (K24DC016312, R13DC003383)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Health Sciences › Health Professions › Speech and Hearing › Voice and Speech Disorders
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Keywords
- speech recognition, conversational speech, speech disorders, personalized speech recognition, domain-specific training, word error rate, linguistic complexity
- MeSH terms
- Adult, Aged, Female, Humans, Male, Middle Aged, Reading, Speech, Speech Disorders, Speech Recognition Software, Young Adult
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Automatic Speech Recognition of Conversational Speech in Individuals With Disordered Speech. https://app.cochat.ai/papers/10.1044/2024_jslhr-24-00045
- The paper
- Tobin, J., Nelson, P., MacDonald, B., Heywood, R., Cave, R., Seaver, K., Desjardins, A., Jiang, P.-P., & Green, J. R. (2024). Automatic Speech Recognition of Conversational Speech in Individuals With Disordered Speech. Journal of Speech, Language, and Hearing Research. https://doi.org/10.1044/2024_jslhr-24-00045
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.