{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T16:10:21Z","timestamp":1772467821156,"version":"3.50.1"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T00:00:00Z","timestamp":1620086400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T00:00:00Z","timestamp":1620086400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Australian Research Council Industry Transformational Training Centre","award":["IC170100030"],"award-info":[{"award-number":["IC170100030"]}]},{"name":"Australian Research Council Industry Transformational Training Centre","award":["IC170100030"],"award-info":[{"award-number":["IC170100030"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2021,9]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Automatic speech recognition (ASR) could potentially improve communication by providing transcriptions of speech in real time. ASR is particularly useful for people with progressive disorders that lead to reduced speech intelligibility or difficulties performing motor tasks. ASR services are usually trained on healthy speech and may not be optimized for impaired speech, creating a barrier for accessing augmented assistance devices. We tested the performance of three state-of-the-art ASR platforms on two groups of people with neurodegenerative disease and healthy controls. We further examined individual differences that may explain errors in ASR services within groups, such as age and sex. Speakers were recorded while reading a standard text. Speech was elicited from individuals with multiple sclerosis, Friedreich\u2019s ataxia, and healthy controls. Recordings were manually transcribed and compared to ASR transcriptions using Amazon Web Services, Google Cloud, and IBM Watson. Accuracy was measured as the proportion of words that were correctly classified. ASR accuracy was higher for controls than clinical groups, and higher for multiple sclerosis compared to Friedreich\u2019s ataxia for all ASR services. Amazon Web Services and Google Cloud yielded higher accuracy than IBM Watson. ASR accuracy decreased with increased disease duration. Age and sex did not significantly affect ASR accuracy. ASR faces challenges for people with neuromuscular disorders. Until improvements are made in recognizing less intelligible speech, the true value of ASR for people requiring augmented assistance devices and alternative communication remains unrealized. We suggest potential methods to improve ASR for those with impaired speech.<\/jats:p>","DOI":"10.1007\/s10772-021-09836-w","type":"journal-article","created":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T07:03:07Z","timestamp":1620111787000},"page":"771-779","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["Automatic speech recognition in neurodegenerative disease"],"prefix":"10.1007","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8306-0206","authenticated-orcid":false,"given":"Benjamin G.","family":"Schultz","sequence":"first","affiliation":[]},{"given":"Venkata S. Aditya","family":"Tarigoppula","sequence":"additional","affiliation":[]},{"given":"Gustavo","family":"Noffs","sequence":"additional","affiliation":[]},{"given":"Sandra","family":"Rojas","sequence":"additional","affiliation":[]},{"given":"Anneke","family":"van der Walt","sequence":"additional","affiliation":[]},{"given":"David B.","family":"Grayden","sequence":"additional","affiliation":[]},{"given":"Adam P.","family":"Vogel","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,5,4]]},"reference":[{"key":"9836_CR1","unstructured":"Apple. (2020). Siri for developers. https:\/\/developer.apple.com\/siri\/."},{"issue":"3","key":"9836_CR2","doi-asserted-by":"publisher","first-page":"379","DOI":"10.3758\/BF03192707","volume":"37","author":"R Bakeman","year":"2005","unstructured":"Bakeman, R. (2005). Recommended effect size statistics for repeated measures designs. Behavior Research Methods, 37(3), 379\u2013384.","journal-title":"Behavior Research Methods"},{"issue":"3","key":"9836_CR3","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1016\/j.jml.2012.11.001","volume":"68","author":"DJ Barr","year":"2013","unstructured":"Barr, D. J., Levy, R., Scheepers, C., & Tily, H. J. (2013). Random effects structure for confirmatory hypothesis testing: Keep it maximal. Journal of Memory and Language, 68(3), 255\u2013278.","journal-title":"Journal of Memory and Language"},{"issue":"4","key":"9836_CR4","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1080\/02699200050024001","volume":"14","author":"B Blaney","year":"2000","unstructured":"Blaney, B., & Wilson, J. (2000). Acoustic variability in dysarthria and computer speech recognition. Clinical Linguistics and Phonetics, 14(4), 307\u2013327.","journal-title":"Clinical Linguistics and Phonetics"},{"key":"9836_CR5","doi-asserted-by":"publisher","DOI":"10.1007\/s40860-019-00085-y","author":"L De Russis","year":"2019","unstructured":"De Russis, L., & Corno, F. (2019). On the impact of dysarthric speech on contemporary ASR cloud platforms. Journal of Reliable Intelligent Environments. https:\/\/doi.org\/10.1007\/s40860-019-00085-y.","journal-title":"Journal of Reliable Intelligent Environments"},{"key":"9836_CR6","doi-asserted-by":"publisher","first-page":"104606","DOI":"10.1016\/j.nbd.2019.104606","volume":"132","author":"MB Delatycki","year":"2019","unstructured":"Delatycki, M. B., & Bidichandani, S. I. (2019). Friedreich ataxia-pathogenesis and implications for therapies. Neurobiology of Disease, 132, 104606.","journal-title":"Neurobiology of Disease"},{"issue":"1","key":"9836_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1136\/jmg.37.1.1","volume":"37","author":"MB Delatycki","year":"2000","unstructured":"Delatycki, M. B., Williamson, R., & Forrest, S. M. (2000). Friedreich ataxia: An overview. Journal of Medical Genetics, 37(1), 1\u20138.","journal-title":"Journal of Medical Genetics"},{"key":"9836_CR8","doi-asserted-by":"publisher","DOI":"10.1159\/000287207","author":"J Folker","year":"2010","unstructured":"Folker, J., Murdoch, B., Cahill, L., Delatycki, M., Corben, L., & Vogel, A. (2010). Dysarthria in Friedreich\u2019s ataxia: A perceptual analysis. Folia Phoniatrica et Logopaedica. https:\/\/doi.org\/10.1159\/000287207.","journal-title":"Folia Phoniatrica et Logopaedica"},{"issue":"9","key":"9836_CR9","doi-asserted-by":"publisher","first-page":"2394","DOI":"10.1044\/2017_JSLHR-S-16-0269","volume":"60","author":"L Fontan","year":"2017","unstructured":"Fontan, L., Ferran\u00e9, I., Farinas, J., Pinquier, J., Tardieu, J., Magnen, C., Gaillard, P., Aumont, X., & F\u00fcllgrabe, C. (2017). Automatic speech recognition predicts speech intelligibility and comprehension for listeners with simulated age-related hearing loss. Journal of Speech, Language, and Hearing Research, 60(9), 2394\u20132405.","journal-title":"Journal of Speech, Language, and Hearing Research"},{"key":"9836_CR10","doi-asserted-by":"publisher","first-page":"f7062","DOI":"10.1136\/bmj.f7062","volume":"347","author":"P Gibilisco","year":"2013","unstructured":"Gibilisco, P., & Vogel, A. P. (2013). Friedreich ataxia. BMJ, 347, f7062.","journal-title":"BMJ"},{"issue":"8334","key":"9836_CR11","doi-asserted-by":"publisher","first-page":"1151","DOI":"10.1016\/S0140-6736(83)92879-9","volume":"321","author":"AE Harding","year":"1983","unstructured":"Harding, A. E. (1983). Classification of the hereditary ataxias and paraplegias. The Lancet, 321(8334), 1151\u20131155.","journal-title":"The Lancet"},{"key":"9836_CR12","unstructured":"Hothorn, T., Bretz, F., Westfall, P., & Heiberger, R. M. (2008). Multcomp: Simultaneous inference for general linear hypotheses. R Package Version, 0-1."},{"key":"9836_CR13","doi-asserted-by":"crossref","unstructured":"Jeffreys, H. (1998). The theory of probability. OUP.","DOI":"10.1093\/oso\/9780198503682.001.0001"},{"issue":"6","key":"9836_CR14","doi-asserted-by":"publisher","first-page":"665","DOI":"10.5351\/CSAM.2015.22.6.665","volume":"22","author":"S Kim","year":"2015","unstructured":"Kim, S., & Kim, M. S. (2015). Package \u2018ppcor.\u2019 Communications for Statistical Applications and Methods, 22(6), 665\u2013674.","journal-title":"Communications for Statistical Applications and Methods"},{"key":"9836_CR15","doi-asserted-by":"publisher","first-page":"S391","DOI":"10.1016\/S1353-8020(08)70036-1","volume":"13","author":"T Klockgether","year":"2007","unstructured":"Klockgether, T. (2007). Ataxias. Parkinsonism and Related Disorders, 13, S391\u2013S394.","journal-title":"Parkinsonism and Related Disorders"},{"issue":"2","key":"9836_CR16","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1016\/j.bandl.2009.12.004","volume":"114","author":"F Li\u00e9geois","year":"2010","unstructured":"Li\u00e9geois, F., Morgan, A. T., Stewart, L. H., Cross, J. H., Vogel, A. P., & Vargha-Khadem, F. (2010). Speech and oral motor profile after childhood hemispherectomy. Brain and Language, 114(2), 126\u2013134.","journal-title":"Brain and Language"},{"issue":"12","key":"9836_CR17","doi-asserted-by":"publisher","first-page":"1191","DOI":"10.1080\/14737175.2019.1649142","volume":"19","author":"M Magee","year":"2019","unstructured":"Magee, M., Copland, D., & Vogel, A. P. (2019). Motor speech and non-motor language endophenotypes of Parkinson\u2019s disease. Expert Review of Neurotherapeutics, 19(12), 1191\u20131200.","journal-title":"Expert Review of Neurotherapeutics"},{"key":"9836_CR18","unstructured":"MathWorks. (2019). MATLAB (9.6.0 (2019b)). The MathWorks Inc."},{"key":"9836_CR19","unstructured":"Mazzoni, D., & Dannenberg, R. (2012). Audacity\u00ae 2.0.0. Audacity Team."},{"key":"9836_CR20","doi-asserted-by":"publisher","unstructured":"Mengistu, K. T., & Rudzicz, F. (2011). Comparing humans and automatic speech recognition systems in recognizing dysarthric speech. Lecture notes in computer science (including subseries lecture notes in artificial intelligence and lecture notes in bioinformatics). https:\/\/doi.org\/10.1007\/978-3-642-21043-3-36","DOI":"10.1007\/978-3-642-21043-3-36"},{"key":"9836_CR21","unstructured":"Microsoft. (2020). Cortana: Your personal productivity assistant in Microsoft 365. https:\/\/www.microsoft.com\/en-us\/cortana."},{"key":"9836_CR22","unstructured":"Morey, R. D., Rouder, J. N., & Jamil, T. (2018). BayesFactor: Computation of Bayes Factors for common designs. R package version 0.9.12-4.2. https:\/\/CRAN.R-project. org\/package=BayesFactor. Cited June 30, 2018."},{"issue":"5","key":"9836_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s12311-020-01151-5","volume":"19","author":"G Noffs","year":"2020","unstructured":"Noffs, G., Boonstra, F. M. C., Perera, T., Kolbe, S. C., Stankovich, J., Butzkueven, H., Evans, A., Vogel, A. P., & van der Walt, A. (2020). Acoustic speech analytics are predictive of cerebellar dysfunction in multiple sclerosis. The Cerebellum, 19(5), 1\u201310.","journal-title":"The Cerebellum"},{"issue":"12","key":"9836_CR24","doi-asserted-by":"publisher","first-page":"1202","DOI":"10.1016\/j.autrev.2018.06.010","volume":"17","author":"G Noffs","year":"2018","unstructured":"Noffs, G., Perera, T., Kolbe, S. C., Shanahan, C. J., Boonstra, F. M. C., Evans, A., Butzkueven, H., van der Walt, A., & Vogel, A. P. (2018). What speech can tell us: A systematic review of dysarthria characteristics in Multiple Sclerosis. Autoimmunity Reviews, 17(12), 1202\u20131209.","journal-title":"Autoimmunity Reviews"},{"key":"9836_CR25","unstructured":"Nuance. (2020). Dragon Naturally Speaking software. https:\/\/www.nuance.com\/en-au\/dragon\/support\/dragon-naturallyspeaking.html."},{"key":"9836_CR26","doi-asserted-by":"crossref","unstructured":"Nuijten, M. B., Wetzels, R., Matzke, D., Dolan, C. V., & Wagenmakers, E. J. (2014). BayesMed: Default Bayesian hypothesis tests for correlation, partial correlation, and mediation (R package version 1.0.0.).","DOI":"10.3758\/s13428-014-0470-2"},{"issue":"3","key":"9836_CR27","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1080\/07434610600649971","volume":"22","author":"JS Owens","year":"2006","unstructured":"Owens, J. S. (2006). Accessible information for people with complex communication needs. Augmentative and Alternative Communication, 22(3), 196\u2013208.","journal-title":"Augmentative and Alternative Communication"},{"key":"9836_CR28","unstructured":"Pinheiro, J., Bates, D., DebRoy, S., Sarkar, D., & R Core Team. (2015). nlme: Linear and nonlinear mixed effects models. R package version 3.1-120. R Package Version, 1-3."},{"key":"9836_CR29","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1016\/j.wocn.2017.01.009","volume":"64","author":"S Pinto","year":"2017","unstructured":"Pinto, S., Chan, A., Guimar\u00e3es, I., Rothe-Neves, R., & Sadat, J. (2017). A cross-linguistic perspective to the study of dysarthria in Parkinson\u2019s disease. Journal of Phonetics, 64, 156\u2013167.","journal-title":"Journal of Phonetics"},{"issue":"4","key":"9836_CR30","doi-asserted-by":"publisher","first-page":"897","DOI":"10.1044\/2016_JSLHR-S-16-0140","volume":"60","author":"ML Poole","year":"2017","unstructured":"Poole, M. L., Brodtmann, A., Darby, D., & Vogel, A. P. (2017). Motor speech phenotypes of frontotemporal dementia, primary progressive aphasia, and progressive apraxia of speech. Journal of Speech, Language, and Hearing Research, 60(4), 897\u2013911.","journal-title":"Journal of Speech, Language, and Hearing Research"},{"issue":"1","key":"9836_CR31","doi-asserted-by":"publisher","first-page":"46","DOI":"10.3109\/02699206.2014.954734","volume":"29","author":"ML Poole","year":"2015","unstructured":"Poole, M. L., Wee, J. S., Folker, J. E., Corben, L. A., Delatycki, M. B., & Vogel, A. P. (2015). Nasality in Friedreich ataxia. Clinical Linguistics and Phonetics, 29(1), 46\u201358.","journal-title":"Clinical Linguistics and Phonetics"},{"key":"9836_CR32","unstructured":"Project Euphonia by Google AI. (n.d.)."},{"key":"9836_CR33","unstructured":"R Core Team. (2013). R: A language and environment for statistical computing. R Core Team."},{"issue":"4","key":"9836_CR34","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1080\/aac.17.4.265.275","volume":"17","author":"P Raghavendra","year":"2001","unstructured":"Raghavendra, P., Rosengren, E., & Hunnicutt, S. (2001). An investigation of different degrees of dysarthric speech as input to speaker-adaptive and speaker-dependent recognition systems. Augmentative and Alternative Communication, 17(4), 265\u2013275.","journal-title":"Augmentative and Alternative Communication"},{"issue":"2","key":"9836_CR35","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1044\/2019_JSLHR-19-00099","volume":"63","author":"S Rojas","year":"2020","unstructured":"Rojas, S., Kefalianos, E., & Vogel, A. (2020). How does our voice change as we age? A systematic review and meta-analysis of acoustic and perceptual voice data from healthy adults over 50 years of age. Journal of Speech, Language, and Hearing Research, 63(2), 533\u2013551.","journal-title":"Journal of Speech, Language, and Hearing Research"},{"issue":"11","key":"9836_CR36","doi-asserted-by":"publisher","first-page":"2471","DOI":"10.1007\/s00415-012-6547-x","volume":"259","author":"KM Rosen","year":"2012","unstructured":"Rosen, K. M., Folker, J. E., Vogel, A. P., Corben, L. A., Murdoch, B. E., & Delatycki, M. B. (2012). Longitudinal change in dysarthria associated with Friedreich ataxia: A potential clinical endpoint. Journal of Neurology, 259(11), 2471\u20132477.","journal-title":"Journal of Neurology"},{"issue":"1","key":"9836_CR37","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1080\/07434610012331278904","volume":"16","author":"K Rosen","year":"2000","unstructured":"Rosen, K., & Yampolsky, S. (2000). Automatic speech recognition and a review of its functioning with dysarthric speech. Augmentative and Alternative Communication, 16(1), 48\u201360. https:\/\/doi.org\/10.1080\/07434610012331278904.","journal-title":"Augmentative and Alternative Communication"},{"key":"9836_CR38","unstructured":"Rossum, G. V. (2019). Python Language Reference, version 3. Python Software Foundation."},{"issue":"sup2","key":"9836_CR39","doi-asserted-by":"publisher","first-page":"100","DOI":"10.3109\/14992027.2015.1061708","volume":"54","author":"MR Sch\u00e4dler","year":"2015","unstructured":"Sch\u00e4dler, M. R., Warzybok, A., Hochmuth, S., & Kollmeier, B. (2015). Matrix sentence intelligibility prediction using an automatic speech recognition system. International Journal of Audiology, 54(sup2), 100\u2013107.","journal-title":"International Journal of Audiology"},{"issue":"4","key":"9836_CR40","first-page":"5","volume":"56","author":"W Shih","year":"2020","unstructured":"Shih, W. (2020). Voice revolution. Library Technology Reports, 56(4), 5\u201313.","journal-title":"Library Technology Reports"},{"key":"9836_CR41","unstructured":"Stoppler, M. C. (2019). Multiple sclerosis symptoms, causes, treatment, diagnosis, and life expectancy. Emedicinehealth. https:\/\/www.emedicinehealth.com\/multiple_sclerosis\/article_em.htm."},{"issue":"1","key":"9836_CR42","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1080\/07434619812331278196","volume":"14","author":"N Thomas-Stonell","year":"1998","unstructured":"Thomas-Stonell, N., Kotler, A.-L., Leeper, H., & Doyle, P. (1998). Computerized speech recognition: Influence of intelligibility and perceptual consistency on recognition accuracy. Augmentative and Alternative Communication, 14(1), 51\u201356.","journal-title":"Augmentative and Alternative Communication"},{"key":"9836_CR43","unstructured":"Van Riper, C. (1963). Speech correction principles and methods (Vol. 7, pp. 176\u2013177). Prentice Hall."},{"issue":"2","key":"9836_CR44","doi-asserted-by":"publisher","first-page":"243.e9","DOI":"10.1016\/j.jvoice.2016.04.015","volume":"31","author":"AP Vogel","year":"2017","unstructured":"Vogel, A. P., Wardrop, M. I., Folker, J. E., Synofzik, M., Corben, L. A., Delatycki, M. B., & Awan, S. N. (2017). Voice in Friedreich ataxia. Journal of Voice, 31(2), 243.e9-243.e19. https:\/\/doi.org\/10.1016\/j.jvoice.2016.04.015.","journal-title":"Journal of Voice"},{"issue":"3","key":"9836_CR45","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1016\/S1474-4422(18)30443-5","volume":"18","author":"MT Wallin","year":"2019","unstructured":"Wallin, M. T., Culpepper, W. J., Nichols, E., Bhutta, Z. A., Gebrehiwot, T. T., Hay, S. I., Khalil, I. A., Krohn, K. J., Liang, X., & Naghavi, M. (2019). Global, regional, and national burden of multiple sclerosis 1990\u20132016: A systematic analysis for the Global Burden of Disease Study 2016. The Lancet Neurology, 18(3), 269\u2013285.","journal-title":"The Lancet Neurology"},{"issue":"2 Pt 2","key":"9836_CR46","doi-asserted-by":"publisher","first-page":"1246","DOI":"10.1121\/1.425977","volume":"105","author":"PCM Wong","year":"1999","unstructured":"Wong, P. C. M., & Diehl, R. L. (1999). The effect of reduced tonal space in Parkinsonian speech on the perception of Cantonese tones. Journal of the Acoustical Society of America, 105(2 Pt 2), 1246.","journal-title":"Journal of the Acoustical Society of America"},{"key":"9836_CR47","doi-asserted-by":"publisher","DOI":"10.1080\/10400435.2010.483646","author":"V Young","year":"2010","unstructured":"Young, V., & Mihailidis, A. (2010). Difficulties in automatic speech recognition of dysarthric speakers and implications for speech-based applications used by the elderly: A literature review. Assistive Technology. https:\/\/doi.org\/10.1080\/10400435.2010.483646.","journal-title":"Assistive Technology"},{"key":"9836_CR48","unstructured":"Zhang, A. (2017). Speech recognition (version 3.8). May."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-021-09836-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-021-09836-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-021-09836-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,30]],"date-time":"2024-08-30T03:58:39Z","timestamp":1724990319000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-021-09836-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,4]]},"references-count":48,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2021,9]]}},"alternative-id":["9836"],"URL":"https:\/\/doi.org\/10.1007\/s10772-021-09836-w","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,4]]},"assertion":[{"value":"19 August 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 March 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 May 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"APV is Chief Science Officer of Redenlab, a speech biomarker company.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}