{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T05:38:06Z","timestamp":1776922686521,"version":"3.51.2"},"reference-count":88,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100002701","name":"Korea Ministry of Education","doi-asserted-by":"publisher","award":["RS-2023-00275579"],"award-info":[{"award-number":["RS-2023-00275579"]}],"id":[{"id":"10.13039\/501100002701","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002380","name":"Hanyang University","doi-asserted-by":"publisher","award":["HY-202500000001616"],"award-info":[{"award-number":["HY-202500000001616"]}],"id":[{"id":"10.13039\/501100002380","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Speech Communication"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1016\/j.specom.2026.103393","type":"journal-article","created":{"date-parts":[[2026,3,29]],"date-time":"2026-03-29T20:20:47Z","timestamp":1774815647000},"page":"103393","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Diagnosis-aware multitask fine-tuning of Whisper for dysarthric speech recognition"],"prefix":"10.1016","volume":"180","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8487-5743","authenticated-orcid":false,"given":"Yoona","family":"Chung","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeongmin","family":"Hong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaehyuk","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3743-3550","authenticated-orcid":false,"given":"Eunchan","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.specom.2026.103393_bib0001","unstructured":"AI-Hub. 2021. Speech recognition data for dysarthria. https:\/\/aihub.or.kr\/aihubdata\/data\/view.do?dataSetSn=608 (accessed 30 July 2025)."},{"key":"10.1016\/j.specom.2026.103393_bib0002","first-page":"1","article-title":"Automatic speech recognition (ASR) for the diagnosis of pronunciation of speech sound disorders in Korean children","author":"Ahn","year":"2024","journal-title":"Clin. Linguist. Phon."},{"key":"10.1016\/j.specom.2026.103393_bib0003","doi-asserted-by":"crossref","first-page":"39982","DOI":"10.1109\/ACCESS.2025.3547041","article-title":"Automatic classification of speech dysarthric intelligibility levels using textual feature","volume":"13","author":"Alharbi","year":"2025","journal-title":"IEEE Access"},{"issue":"1","key":"10.1016\/j.specom.2026.103393_bib0004","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-021-02487-6","article-title":"Distinctive prosodic features of people with autism spectrum disorder: a systematic review and meta-analysis study","volume":"11","author":"Asghari","year":"2021","journal-title":"Sci. Rep."},{"key":"10.1016\/j.specom.2026.103393_bib0005","first-page":"12449","article-title":"Wav2vec 2.0: a framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"19","key":"10.1016\/j.specom.2026.103393_bib0006","doi-asserted-by":"crossref","first-page":"6936","DOI":"10.3390\/app10196936","article-title":"Ksponspeech: Korean spontaneous speech corpus for automatic speech recognition","volume":"10","author":"Bang","year":"2020","journal-title":"Appl. Sci."},{"key":"10.1016\/j.specom.2026.103393_bib0007","series-title":"Interspeech","first-page":"228","article-title":"Recognition of dysarthric speech using voice parameters for speaker adaptation and multi-taper spectral estimation","author":"Bhat","year":"2016"},{"key":"10.1016\/j.specom.2026.103393_bib0008","unstructured":"Boersma, P., Weenink, D. 2018. Praat: doing phonetics by computer [computer software] version 6.0.37."},{"key":"10.1016\/j.specom.2026.103393_bib0009","series-title":"Proceedings of the Institute of Phonetic Sciences","first-page":"97","article-title":"Accurate short-term analysis of the fundamental frequency and the harmonics-to-noise ratio of a sampled sound","volume":"17","author":"Boersma","year":"1993"},{"issue":"1","key":"10.1016\/j.specom.2026.103393_bib0010","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"issue":"1","key":"10.1016\/j.specom.2026.103393_bib0011","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2009\/308340","article-title":"Modelling errors in automatic speech recognition for dysarthric speakers","volume":"2009","author":"Caballero Morales","year":"2009","journal-title":"EURASIP J. Adv. Signal Process."},{"issue":"2","key":"10.1016\/j.specom.2026.103393_bib0012","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1080\/02687038.2010.541469","article-title":"Language as a stressor in aphasia","volume":"25","author":"Cahana-Amitay","year":"2011","journal-title":"Aphasiology"},{"key":"10.1016\/j.specom.2026.103393_bib0013","doi-asserted-by":"crossref","first-page":"1170","DOI":"10.1109\/TASLPRO.2025.3543975","article-title":"Multimodal audio-based disease prediction with transformer-based hierarchical fusion network","volume":"33","author":"Cai","year":"2025","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.specom.2026.103393_bib0015","series-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","first-page":"785","article-title":"Xgboost: a scalable tree boosting system","author":"Chen","year":"2016"},{"key":"10.1016\/j.specom.2026.103393_bib0016","series-title":"IEEE Spoken Language Technology Workshop (SLT)","first-page":"953","article-title":"Speech recognition-based feature extraction for enhanced automatic severity classification in dysarthric speech","author":"Choi","year":"2024"},{"key":"10.1016\/j.specom.2026.103393_bib0017","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijmedinf.2023.105112","article-title":"Development and benchmarking of a Korean audio speech recognition model for clinician-patient conversations in radiation oncology clinics","volume":"176","author":"Chun","year":"2023","journal-title":"Int. J. Med. Inform."},{"issue":"2","key":"10.1016\/j.specom.2026.103393_bib0018","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1111\/j.2517-6161.1958.tb00292.x","article-title":"The regression analysis of binary sequences","volume":"20","author":"Cox","year":"1958","journal-title":"J. R. Stat. Soc. B"},{"issue":"4","key":"10.1016\/j.specom.2026.103393_bib0019","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1080\/13682820500126049","article-title":"Intervention for children with severe speech disorder: a comparison of two approaches","volume":"40","author":"Crosbie","year":"2005","journal-title":"Int. J. Lang. Commun. Disord."},{"issue":"3","key":"10.1016\/j.specom.2026.103393_bib0020","first-page":"309","article-title":"Dysarthric speech: a comparison of computerized speech recognition and listener intelligibility","volume":"34","author":"Doyle","year":"1997","journal-title":"J. Rehabil. Res. Dev."},{"key":"10.1016\/j.specom.2026.103393_bib0021","series-title":"Motor Speech Disorders: Substrates, Differential Diagnosis, and Management","author":"Duffy","year":"2012"},{"key":"10.1016\/j.specom.2026.103393_bib0022","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1186\/1471-2288-12-78","article-title":"T-tests, non-parametric tests, and large studies\u2014a paradox of statistical practice","volume":"12","author":"Fagerland","year":"2012","journal-title":"BMC Med. Res. Methodol."},{"key":"10.1016\/j.specom.2026.103393_bib0023","series-title":"Interspeech","first-page":"778","article-title":"Jitter and shimmer measurements for speaker recognition","author":"Farr\u00fas","year":"2007"},{"issue":"3","key":"10.1016\/j.specom.2026.103393_bib0025","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1080\/07434619512331277289","article-title":"Dysarthric speakers\u2019 intelligibility and speech characteristics in relation to computer speech recognition","volume":"11","author":"Ferrier","year":"1995","journal-title":"Augment. Altern. Commun."},{"issue":"57","key":"10.1016\/j.specom.2026.103393_bib0026","first-page":"233","article-title":"An important contribution to nonparametric discriminant analysis and density estimation","volume":"3","author":"Fix","year":"1951","journal-title":"Int. Stat. Rev."},{"issue":"5","key":"10.1016\/j.specom.2026.103393_bib0027","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: a gradient boosting machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann. Statist."},{"key":"10.1016\/j.specom.2026.103393_bib0028","doi-asserted-by":"crossref","first-page":"2597","DOI":"10.1109\/TASLP.2022.3195113","article-title":"Speaker adaptation using spectro-temporal deep features for dysarthric and elderly speech recognition","volume":"30","author":"Geng","year":"2022","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.specom.2026.103393_bib0029","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.specom.2020.04.006","article-title":"Analytic phase features for dysarthric speech detection and intelligibility assessment","volume":"121","author":"Gurugubelli","year":"2020","journal-title":"Speech Commun."},{"issue":"5","key":"10.1016\/j.specom.2026.103393_bib0030","doi-asserted-by":"crossref","first-page":"586","DOI":"10.1016\/j.medengphy.2006.06.009","article-title":"A speech-controlled environmental control system for people with severe dysarthria","volume":"29","author":"Hawley","year":"2007","journal-title":"Med. Eng. Phys."},{"issue":"12","key":"10.1016\/j.specom.2026.103393_bib0033","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1044\/persp3.SIG12.99","article-title":"The cost of not addressing the communication barriers faced by hospitalized patients","volume":"3","author":"Hurtig","year":"2018","journal-title":"Perspect. ASHA Spec. Interest Groups"},{"key":"10.1016\/j.specom.2026.103393_bib0034","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.wocn.2018.07.001","article-title":"Introducing parselmouth: a Python interface to Praat","volume":"71","author":"Jadoul","year":"2018","journal-title":"J. Phon."},{"issue":"8","key":"10.1016\/j.specom.2026.103393_bib0035","doi-asserted-by":"crossref","first-page":"4951","DOI":"10.1109\/JBHI.2024.3392829","article-title":"Exploring the impact of fine-tuning the wav2vec2 model in database-independent detection of dysarthric speech","volume":"28","author":"Javanmardi","year":"2024","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"10.1016\/j.specom.2026.103393_bib0036","unstructured":"Jeon, H.S., 2025. Computing Korean STT error rates. https:\/\/github.com\/hyeonsangjeon\/computing-Korean-STT-error-rates (accessed 30 July 2025)."},{"issue":"1","key":"10.1016\/j.specom.2026.103393_bib0037","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1016\/j.bbe.2015.11.004","article-title":"Fully automated speaker identification and intelligibility assessment in dysarthria disease using auditory knowledge","volume":"36","author":"Kadi","year":"2016","journal-title":"Biocybern. Biomed. Eng."},{"issue":"5","key":"10.1016\/j.specom.2026.103393_bib0038","doi-asserted-by":"crossref","first-page":"687","DOI":"10.7326\/ANNALS-24-02904","article-title":"Impacts of communication type and quality on patient safety incidents: a systematic review","volume":"178","author":"Keshtkar","year":"2025","journal-title":"Ann. Intern. Med."},{"key":"10.1016\/j.specom.2026.103393_bib0039","series-title":"ICASSPW","first-page":"760","article-title":"Gated low-rank adaptation for personalized code-switching automatic speech recognition on the low-spec devices","author":"Kim","year":"2024"},{"key":"10.1016\/j.specom.2026.103393_bib0040","series-title":"Proc. 3rd Workshop Multi-Lingual Representation Learning (MRL)","first-page":"85","article-title":"Adapt and prune strategy for multilingual speech foundational model on low-resourced languages","author":"Kim","year":"2023"},{"issue":"4","key":"10.1016\/j.specom.2026.103393_bib0041","doi-asserted-by":"crossref","first-page":"81","DOI":"10.13064\/KSSS.2020.12.4.081","article-title":"Building a Korean conversational speech database in the emergency medical domain","volume":"12","author":"Kim","year":"2020","journal-title":"Phonetics Speech Sci."},{"key":"10.1016\/j.specom.2026.103393_bib0042","series-title":"Proceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency","first-page":"1672","article-title":"Careless whisper: speech-to-text hallucination harms","author":"Koenecke","year":"2024"},{"issue":"3","key":"10.1016\/j.specom.2026.103393_bib0043","doi-asserted-by":"crossref","first-page":"287","DOI":"10.3233\/JND-190436","article-title":"Dysphagia and dysarthria in children with neuromuscular diseases, a prevalence study","volume":"7","author":"Kooi-van Es","year":"2020","journal-title":"J. Neuromuscul. Dis."},{"key":"10.1016\/j.specom.2026.103393_bib0044","unstructured":"Korea Employment Agency for the Disabled Employment Development Institute, 2023. 2023 Survey on employment status of disabled persons in enterprises."},{"key":"10.1016\/j.specom.2026.103393_bib0045","series-title":"Proceedings of Interspeech 2024","first-page":"5058","article-title":"Balanced-Wav2Vec: enhancing stability and robustness of representation learning through sample reweighting techniques","author":"Lee","year":"2024"},{"key":"10.1016\/j.specom.2026.103393_bib0046","series-title":"IEEE Int. Conf. Consum. Electron. (ICCE)","first-page":"1","article-title":"AI-enabled speech monitoring for dysarthria detection in consumer electronics","author":"Lee","year":"2025"},{"issue":"1","key":"10.1016\/j.specom.2026.103393_bib0047","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1177\/002383095800100103","article-title":"Brain disorders and language analysis","volume":"1","author":"Luria","year":"1958","journal-title":"Lang. Speech"},{"key":"10.1016\/j.specom.2026.103393_bib0048","series-title":"Proc. Python Sci. Conf","doi-asserted-by":"crossref","first-page":"18","DOI":"10.25080\/Majora-7b98e3ed-003","article-title":"Librosa: audio and music signal analysis in python","author":"McFee","year":"2015"},{"key":"10.1016\/j.specom.2026.103393_bib0049","unstructured":"Ministry of Health and Welfare, 2023. Survey on the status of persons with disabilities."},{"issue":"7","key":"10.1016\/j.specom.2026.103393_bib0050","doi-asserted-by":"crossref","first-page":"950","DOI":"10.1080\/02687038.2020.1759772","article-title":"Prevalence of aphasia and dysarthria among inpatient stroke survivors: describing the population, therapy provision and outcomes on discharge","volume":"35","author":"Mitchell","year":"2021","journal-title":"Aphasiology"},{"key":"10.1016\/j.specom.2026.103393_bib0051","article-title":"Whistle-blowing ASRs: evaluating the need for more inclusive speech recognition systems","author":"Moore","year":"2018","journal-title":"Interspeech"},{"key":"10.1016\/j.specom.2026.103393_bib0052","first-page":"138","article-title":"Voice recognition algorithms using mel frequency cepstral coefficient (MFCC) and dynamic time warping (DTW) techniques","volume":"2","author":"Muda","year":"2010","journal-title":"J. Comput."},{"issue":"1","key":"10.1016\/j.specom.2026.103393_bib0053","first-page":"1","article-title":"Non-invasive stroke diagnosis using speech data from dysarthria patients","volume":"2024","author":"Mun","year":"2024","journal-title":"Annu. Int. Conf. IEEE Eng. Med. Biol. Soc."},{"issue":"1","key":"10.1016\/j.specom.2026.103393_bib0054","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0086285","article-title":"Severity-based adaptation with limited data for ASR to aid dysarthric speakers","volume":"9","author":"Mustafa","year":"2014","journal-title":"PLOS One"},{"key":"10.1016\/j.specom.2026.103393_bib0055","doi-asserted-by":"crossref","first-page":"1182","DOI":"10.1162\/tacl_a_00696","article-title":"Hypernetworks for personalizing ASR to atypical speech","volume":"12","author":"M\u00fcller-Eberstein","year":"2024","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.specom.2026.103393_bib0056","series-title":"ICASSP 2025 - IEEE Int. Conf. Acoust., Speech Signal Process","first-page":"1","article-title":"Improved recognition of the speech of people with Parkinson\u2019s who stutter","author":"Na","year":"2025"},{"key":"10.1016\/j.specom.2026.103393_bib0057","series-title":"2024 Asia Pacific Signal Inf. Process. Assoc. Annu. Summit Conf. (APSIPA ASC)","first-page":"1","article-title":"A comparative study on the biases of age, gender, dialects, and L2 speakers of automatic speech recognition for Korean language","author":"Na","year":"2024"},{"key":"10.1016\/j.specom.2026.103393_bib0058","series-title":"Comparison of Outpatient Treatment Time, Type for Disabled and Non-Disabled Patients and Study of Factors Influencing Outpatient Treatment","year":"2020"},{"issue":"2","key":"10.1016\/j.specom.2026.103393_bib0059","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1044\/2023_JSLHR-23-00411","article-title":"Articulatory and vocal fold movement patterns during loud speech in children with cerebral palsy","volume":"67","author":"Nip","year":"2024","journal-title":"J. Speech Lang. Hear. Res."},{"key":"10.1016\/j.specom.2026.103393_bib0060","unstructured":"OpenAI, 2025. Whisper. https:\/\/github.com\/openai\/whisper (accessed 30 July 2025)."},{"key":"10.1016\/j.specom.2026.103393_bib0061","series-title":"Interspeech","first-page":"2613","article-title":"SpecAugment: a simple data augmentation method for automatic speech recognition","author":"Park","year":"2019"},{"issue":"3","key":"10.1016\/j.specom.2026.103393_bib0062","doi-asserted-by":"crossref","first-page":"1416","DOI":"10.3390\/app15031416","article-title":"Real-time communication aid system for Korean dysarthric speech","volume":"15","author":"Park","year":"2025","journal-title":"Appl. Sci."},{"key":"10.1016\/j.specom.2026.103393_bib0063","series-title":"Interspeech","first-page":"1522","article-title":"Using voice quality features to improve short-utterance, text-independent speaker verification systems","author":"Park","year":"2017"},{"key":"10.1016\/j.specom.2026.103393_bib0064","series-title":"Proc. 8th Eur. Conf. Speech Commun. Technol. (Eurospeech 2003)","article-title":"A syllable segmentation algorithm for English and Italian","author":"Petrillo","year":"2003"},{"key":"10.1016\/j.specom.2026.103393_bib0065","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume":"2023","author":"Radford","year":"2023","journal-title":"Int. Conf. Mach. Learn."},{"issue":"768","key":"10.1016\/j.specom.2026.103393_bib0066","first-page":"12","article-title":"Whisper features for dysarthric severity-level classification","volume":"12","author":"Rathod","year":"2023","journal-title":"Small"},{"issue":"5","key":"10.1016\/j.specom.2026.103393_bib0067","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0154971","article-title":"Predicting speech intelligibility decline in amyotrophic lateral sclerosis based on the deterioration of individual speech subsystems","volume":"11","author":"Rong","year":"2016","journal-title":"PLOS One"},{"key":"10.1016\/j.specom.2026.103393_bib0068","doi-asserted-by":"crossref","DOI":"10.3389\/fcomp.2022.770210","article-title":"Characterizing dysarthria diversity for automatic speech recognition: a tutorial from the clinical perspective","volume":"4","author":"Rowe","year":"2022","journal-title":"Front. Comput. Sci."},{"key":"10.1016\/j.specom.2026.103393_bib0069","series-title":"ICASSP 2025 - IEEE Int. Conf. Acoust., Speech Signal Process","first-page":"1","article-title":"Noise-agnostic multitask whisper training for reducing false alarm errors in call-for-help detection","author":"Ryu","year":"2025"},{"issue":"4","key":"10.1016\/j.specom.2026.103393_bib0070","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1016\/S0385-8146(03)00093-2","article-title":"Effect of the loss of auditory feedback on segmental parameters of vowels of postlingually deafened speakers","volume":"30","author":"Schenk","year":"2003","journal-title":"Auris Nasus Larynx"},{"key":"10.1016\/j.specom.2026.103393_bib0071","first-page":"1","article-title":"Extending Whisper for Korean-English code-switching speech recognition","author":"Seong","year":"2025","journal-title":"IEEE Int. Conf. Consum. Electron. (ICCE)"},{"key":"10.1016\/j.specom.2026.103393_bib0072","series-title":"Interspeech","first-page":"784","article-title":"Personalizing ASR For dysarthric and accented speech with limited data","author":"Shor","year":"2019"},{"key":"10.1016\/j.specom.2026.103393_bib0073","series-title":"ICASSP 2025 - IEEE Int. Conf. Acoust., Speech Signal Process","first-page":"1","article-title":"Robust cross-etiology and speaker-independent dysarthric speech recognition","author":"Singh","year":"2025"},{"issue":"1\u20132","key":"10.1016\/j.specom.2026.103393_bib0074","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1016\/j.jns.2011.07.020","article-title":"Aspects of speech rate and regularity in Parkinson\u2019s disease","volume":"310","author":"Skodda","year":"2011","journal-title":"J. Neurol. Sci."},{"key":"10.1016\/j.specom.2026.103393_bib0075","doi-asserted-by":"crossref","DOI":"10.1016\/j.msard.2025.106458","article-title":"Prevalence of dysarthria in the multiple sclerosis population: a systematic review and meta-analysis","volume":"98","author":"Smyrni","year":"2025","journal-title":"Mult. Scler. Relat. Disord."},{"issue":"1","key":"10.1016\/j.specom.2026.103393_bib0076","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/97.736233","article-title":"A statistical model-based voice activity detection","volume":"6","author":"Sohn","year":"1999","journal-title":"IEEE Signal Process. Lett."},{"issue":"9","key":"10.1016\/j.specom.2026.103393_bib0077","doi-asserted-by":"crossref","first-page":"2964","DOI":"10.1044\/2024_JSLHR-24-00049","article-title":"Automatic speech recognition in primary progressive apraxia of speech","volume":"67","author":"Tetzloff","year":"2024","journal-title":"J. Speech Lang. Hear. Res."},{"key":"10.1016\/j.specom.2026.103393_bib0078","series-title":"Findings Assoc. Comput. Linguist.","first-page":"4926","article-title":"Advocating character error rate for multilingual ASR evaluation","author":"Thennal","year":"2025"},{"issue":"5","key":"10.1016\/j.specom.2026.103393_bib0079","doi-asserted-by":"crossref","first-page":"975","DOI":"10.1016\/j.jvoice.2022.03.021","article-title":"The effect of the MFCC frame length in automatic voice pathology detection","volume":"38","author":"Tirronen","year":"2024","journal-title":"J. Voice"},{"issue":"5","key":"10.1016\/j.specom.2026.103393_bib0080","doi-asserted-by":"crossref","first-page":"3005","DOI":"10.1121\/1.4919349","article-title":"Toward a consensus on symbolic notation of harmonics, resonances, and formants in vocalization","volume":"137","author":"Titze","year":"2015","journal-title":"J. Acoust. Soc. Am."},{"key":"10.1016\/j.specom.2026.103393_bib0081","series-title":"ICASSP 2022 - IEEE Int. Conf. Acoust., Speech Signal Process","first-page":"6637","article-title":"Personalized automatic speech recognition trained on small disordered speech datasets","author":"Tobin","year":"2022"},{"key":"10.1016\/j.specom.2026.103393_bib0082","unstructured":"Vaessen, N., van Leeuwen, D.A., 2024. The effect of batch size on contrastive self-supervised speech representation learning. arXiv. Available from: https:\/\/arxiv.org\/abs\/2402.13723."},{"key":"10.1016\/j.specom.2026.103393_bib0083","article-title":"Support vector method for function approximation, regression estimation and signal processing","volume":"9","author":"Vapnik","year":"1996","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.specom.2026.103393_bib0084","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.specom.2026.103393_bib0085","series-title":"APCIT 2024 - Asia Pac. Conf. Innov. Technol","first-page":"1","article-title":"Leveraging OpenAI whisper model to improve speech recognition for dysarthric individuals","author":"Vinotha","year":"2024"},{"key":"10.1016\/j.specom.2026.103393_bib0086","doi-asserted-by":"crossref","first-page":"82479","DOI":"10.1109\/ACCESS.2025.3568342","article-title":"Empowering dysarthric communication: hybrid transformer-CTC based speech recognition system","volume":"13","author":"Vinotha","year":"2025","journal-title":"IEEE Access"},{"issue":"8","key":"10.1016\/j.specom.2026.103393_bib0087","doi-asserted-by":"crossref","first-page":"772","DOI":"10.1080\/02699206.2019.1595735","article-title":"Estimates of the prevalence of speech and motor speech disorders in adolescents with Down syndrome","volume":"33","author":"Wilson","year":"2019","journal-title":"Clin. Linguist. Phon."},{"issue":"3","key":"10.1016\/j.specom.2026.103393_bib0088","doi-asserted-by":"crossref","first-page":"320","DOI":"10.3390\/brainsci15030320","article-title":"Vocal feature changes for monitoring Parkinson\u2019s disease progression\u2014a systematic review","volume":"15","author":"Wright","year":"2025","journal-title":"Brain Sci."},{"key":"10.1016\/j.specom.2026.103393_bib0089","first-page":"1","article-title":"Post-stroke dysarthria voice recognition based on fusion feature MSA and 1D","author":"Wujian","year":"2024","journal-title":"Comput. Methods Biomech. Biomed. Eng."},{"key":"10.1016\/j.specom.2026.103393_bib0090","doi-asserted-by":"crossref","DOI":"10.1016\/j.csl.2023.101514","article-title":"A mobile application using automatic speech analysis for classifying Alzheimer\u2019s disease and mild cognitive impairment","volume":"81","author":"Yamada","year":"2023","journal-title":"Comput. Speech Lang."},{"key":"10.1016\/j.specom.2026.103393_bib0091","series-title":"Interspeech","first-page":"4838","article-title":"Automatic severity classification of Korean dysarthric speech using phoneme-level pronunciation features","author":"Yeo","year":"2021"},{"key":"10.1016\/j.specom.2026.103393_bib0092","unstructured":"Zhou, Y., Xiong, C., Socher, R., 2017. Improved regularization techniques for end-to-end speech recognition. arXiv. Available from: http:\/\/arxiv.org\/abs\/1712.07108."}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639326000415?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639326000415?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T04:46:00Z","timestamp":1776919560000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167639326000415"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":88,"alternative-id":["S0167639326000415"],"URL":"https:\/\/doi.org\/10.1016\/j.specom.2026.103393","relation":{},"ISSN":["0167-6393"],"issn-type":[{"value":"0167-6393","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Diagnosis-aware multitask fine-tuning of Whisper for dysarthric speech recognition","name":"articletitle","label":"Article Title"},{"value":"Speech Communication","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.specom.2026.103393","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"103393"}}