Operationalizing Clinical Speech Analytics: Moving From Features to Measures for Real-World Clinical Impact
Open accessAbstract
Objective: This research note advocates for a methodological shift in clinical speech analytics, emphasizing the transition from high-dimensional speech feature representations to clinically validated speech measures designed to operationalize clinically relevant constructs of interest. The aim is to enhance model generalizability and clinical applicability in real-world settings. Method: We outline the challenges of using conventional supervised machine learning models in clinical speech analytics, particularly their limited generalizability and interpretability. We propose a new framework focusing on speech measures that are closely tied to specific speech constructs and have undergone rigorous validation. This research note discusses a case study involving the development of a measure for articulatory precision in amyotrophic lateral sclerosis (ALS), detailing the process from ideation through Food and Drug Administration (FDA) breakthrough status designation. Results: The case study demonstrates how the operationalization of the articulatory precision construct into a quantifiable measure yields robust, clinically meaningful results. The measure's validation followed the V3 framework (verification, analytical validation, and clinical validation), showing high correlation with clinical status and speech intelligibility. The practical application of these measures is exemplified in a clinical trial and designation by the FDA as a breakthrough status device, underscoring their real-world impact. Conclusions: Transitioning from speech features to speech measures offers a more targeted approach for developing speech analytics tools in clinical settings. This shift ensures that models are not only technically sound but also clinically relevant and interpretable, thereby bridging the gap between laboratory research and practical health care applications. We encourage further exploration and adoption of this approach for developing interpretable speech representations tailored to specific clinical needs.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
Clinical AI can be well suited to assessing or monitoring an individual's specific speech and language abilities, after the diagnostics have been considered by a human clinician in the loop.
“In contrast, clinical AI can indeed be well suited to assessing or monitoring an individual's specific speech and language abilities, after the diagnostics have been considered by a human clinician in the loop (e.g., Liss & Berisha, 2024;Ramanarayanan et al., 2022).”
From Equipping Speech-Language Clinicians for the Critical Appraisal of an Artificial Intelligence–Driven, Evidence-Based Future (2025) · cites this paper as Liss & Berisha, 2024
The Case Study: Articulatory Precision in ALS describes AI-derived speech measures used to identify deterioration or improvement, supporting assessment and monitoring of a specific speech ability. The paper does not establish the claimed sequence in which a human clinician considers the diagnostics before AI assessment or monitoring, and its demonstrated use concerns speech in ALS rather than speech and language abilities generally. (LLM, conf=0.85)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
No references could be resolved yet.
Research works printed but not linked: 21
- Allen, M. J., & Yen, W. M. (2001). Introduction to measurement theory. Waveland Press.
- Berisha, V., Krantsevich, C., Hahn, P. R., Hahn, S., Dasarathy, G., Turaga, P., & Liss, J. (2021). Digital medicine and the curse of dimensionality. npj Digital Medicine, 4(1), Article 153. 10.1038/s41746-021-00521-5 PMC8553745 34711924 · DOI · Paper page
- Berisha, V., Krantsevich, C., Stegmann, G., Hahn, S., & Liss, J. (2022). Are reported accuracies in the clinical speech machine learning literature overoptimistic? In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH (Vol. 2022, pp. 2453– 2457).
- Borrie, S. A., Wynn, C. J., Berisha, V., & Barrett, T. S. (2022). From speech acoustics to communicative participation in dysarthria: Toward a causal framework. Journal of Speech, Language, and Hearing Research, 65(2), 405– 418. 10.1044/2021_JSLHR-21-00306 PMC9132139 34958608 · DOI
- Börjesson, M., Hartelius, L., & Laakso, K. (2021). Communicative participation in people with amyotrophic lateral sclerosis. Folia Phoniatrica et Logopaedica, 73(2), 101– 108. 10.1159/000505022 31918429 PMC7949226 · DOI
- Bunton, K., Kent, R. D., Duffy, J. R., Rosenbek, J. C., & Kent, J. F. (2007). Listener agreement for auditory-perceptual ratings of dysarthria. Neurology, 50(6), 1481– 1495. 10.1044/1092-4388(2007/102) 18055769 · DOI
- Coretta, S., Casillas, J. V., Roessig, S., Franke, M., Ahn, B., Al-Hoorie, A. H., Al-Tamimi, J., Alotaibi, N. E., AlShakhori, M. K., Altmiller, R. M., Arantes, P., Athanasopoulou, A., Baese-Berk, M. M., Bailey, G., Sangma, C. B. A., Beier, E. J., Benavides, G. M., Benker, N., BensonMeyer, E. P., … Roettger, T. B. (2023). Multidimensional signals and analytic flexibility: Estimating degrees of freedom in human-speech analyses. Advances in Methods and Practices in Psychological Science, 6(3). 10.1177/25152459231162567 · DOI
- Duffy, J. R. (2020). Motor speech disorders: Substrates, differential diagnosis, and management (4th ed.). Elsevier.
- Ferrer Riesgo, C. A., & Nöth, E. (2020). What makes the cepstral peak prominence different to other acoustic correlates of vocal quality? Journal of Voice, 34(5), 806.e1– 806.e6. 10.1016/j.jvoice.2019.01.004 30683614 · DOI
- Fleiss, J. L. (1999). The design and analysis of clinical experiments. Wiley. 10.1002/9781118032923 · DOI
- Goldsack, J. C., Coravos, A., Bakker, J. P., Bent, B., Dowling, A. V., Fitzer-Attas, C., Godfrey, A., Godino, J. G., Gujar, N., Izmailova, E., Manta, C., Peterson, B., Vandendriessche, B., Wood, W. A., Wang, K. W., & Dunn, J. (2020). Verification, analytical validation, and clinical validation (V3): The foundation of determining fit-for-purpose for Biometric Monitoring Technologies (BioMeTs). npj Digital Medicine, 3(1), Article 55. 10.1038/s41746-020-0260-4 PMC7156507 32337371 · DOI · Paper page
- Panayotov, V., Chen, G., Povey, D., & Khudanpur, S. (2015, April). Librispeech: An ASR corpus based on public domain audio books. In 2015 IEEE international Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 5206– 5210). IEEE.
- Rutkove, S. B., Narayanaswami, P., Berisha, V., Liss, J., Hahn, S., Shelton, K., Qi, K., Pandeya, S., & Shefner, J. M. (2020). Improved ALS clinical trials through frequent at-home self-assessment: A proof of concept study. Annals of Clinical and Translational Neurology, 7(7), 1148– 1157. 10.1002/acn3.51096 32515889 PMC7359124 · DOI
- Rutkove, S. B., Qi, K., Shelton, K., Liss, J., Berisha, V., & Shefner, J. M. (2019). ALS longitudinal studies with frequent data collection at home: Study design and baseline data. Amyotrophic Lateral Sclerosis and Frontotemporal Degeneration, 20(1–2), 61– 67. 10.1080/21678421.2018.1541095 30486680 PMC6513689 · DOI
- Rybner, A., Jessen, E. T., Mortensen, M. D., Larsen, S. N., Grossman, R., Bilenberg, N., Cantio, C., Jepsen, J. R. M., Weed, E., Simonsen, A., & Fusaroli, R. (2022). Vocal markers of autism: Assessing the generalizability of machine learning models. Autism Research, 15(6), 1018– 1030. 10.1002/aur.2721 35385224 · DOI
- Stegmann, G., Charles, S., Liss, J., Shefner, J., Rutkove, S., & Berisha, V. (2023). A speech-based prognostic model for dysarthria progression in ALS. Amyotrophic Lateral Sclerosis and Frontotemporal Degeneration, 24(7–8), 599– 604. 10.1080/21678421.2023.2222144 PMC10713856 37309077 · DOI
- Stegmann, G. M., Hahn, S., Liss, J., Shefner, J., Rutkove, S. B., Kawabata, K., Bhandari, S., Shelton, K., Duncan, C. J., & Berisha, V. (2020). Repeatability of commonly used speech and language features for clinical applications. Digital Biomarkers, 4(3), 109– 122. 10.1159/000511671 33442573 PMC7772887 · DOI · Paper page
- Stegmann, G. M., Hahn, S., Liss, J., Shefner, J., Rutkove, S., Shelton, K., Duncan, C. J., & Berisha, V. (2020). Early detection and tracking of bulbar changes in ALS via frequent and remote speech analysis. npj Digital Medicine, 3(1), Article 132. 10.1038/s41746-020-00335-x PMC7679375 33299098 · DOI
- Stipancic, K. L., Yunusova, Y., Berry, J. D., & Green, J. R. (2018). Minimally detectable change and minimal clinically important difference of a decline in sentence intelligibility and speaking rate for individuals with amyotrophic lateral sclerosis. Journal of Speech, Language, and Hearing Research, 61(11), 2757– 2771. 10.1044/2018_JSLHR-S-17-0366 PMC6693567 30383220 · DOI
- Tu, M., Grabek, A., Liss, J., & Berisha, V. (2018). Investigating the role of L1 in automatic pronunciation evaluation of L2 speech. In Proceedings of Interspeech (pp. 1636–1640).
- Yawer, B. A., Liss, J., & Berisha, V. (2023). Reliability and validity of a widely-available AI tool for assessment of stress based on speech. Scientific Reports, 13(1), Article 20224. 10.1038/s41598-023-47153-1 PMC10657363 37980431 · DOI
Cited by
Sorted by citations
Berisha, V., & Liss, J. M. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01199-1 · Cited by 41 · see citing works
Self-citationBenway, N. R., & Preston, J. L. (2025) · Language, Speech, and Hearing Services in Schools · doi:10.1044/2025_lshss-24-00085 · Cited by 12 · see citing works
- Authors
- Liss, J., & Berisha, V.
- Affiliations
- Arizona State University (US)
- Corresponding author
- Berisha, Visar
- Venue
- Journal of Speech, Language, and Hearing Research
- Published
- 2024-11-07
- Volume
- 67
- Issue
- 11
- Pages
- 4226-4232
- ISSN
- 1092-4388 (ISSN-L)
- 1558-9102
- PMC
- PMC12379576
- OpenAlex
- W4399369167
- Cited by
- 10
- References
- 0
- Citations by year
- 2026: 5 · 2025: 3 · 2024: 2
- FWCI
- 2.85
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Journal of Speech Language and Hearing Research (publishedVersion, cc-by)
- PubMed Central (publishedVersion, public-domain)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Funders
- National Institutes of Health
- National Institute on Deafness and Other Communication Disorders (R01DC006859, R13DC003383)
- Topics
- Health Sciences › Medicine › Physiology › Voice and Speech Disorders
- Health Sciences › Medicine › Neurology › Amyotrophic Lateral Sclerosis Research
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- articulatory precision, amyotrophic lateral sclerosis, speech intelligibility, model generalization, model interpretability, clinical validation, speech features, clinical trials
- MeSH terms
- Amyotrophic Lateral Sclerosis, Humans, Speech, Speech Production Measurement, Reproducibility of Results
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
