Monitoring ALS from speech articulation kinematics
- 35 Downloads
Patients affected by amyotrophic lateral sclerosis (ALS) show specific dysarthria in their speech resulting in specific marks which could be used to detect early symptoms and monitor the evolution of the disease in time. Classically articulation marks have been mainly based on static premises. Articulation kinematics from acoustic correlates may help in producing measurements depending on the dynamic behaviour of speech. Specifically, distribution functions from the absolute kinematic velocity estimated on a simplified articulation model can be used in establishing distances based on information theory concepts between running speech segments from patients and controls. As an example, several cases of ALS were studied longitudinally using this methodology. The study shows that the performance of dynamic articulation quality correlates may be sensitive and robust in tracking illness progress. Conclusions foresee the use of speech as a valuable monitoring methodology for ALS timely neurodegenerative progression.
KeywordsAmyotrophic lateral sclerosis Neuromotor diseases Kullback–Leibler divergence Speech articulation
This work was supported by Calouste Gulbenkian Foundation and the Portuguese Association of ALS (APELA), as well as by Grant TEC2016-77791-C4-4-R (Plan Nacional de I + D+i, Ministry of Economic Affairs and Competitiveness of Spain).
Compliance with ethical standards
Conflict of interest
The authors declare that this research has been conducted according to the Helsinki Declaration on ethical standards, it has been carried on public or non-profit funding, and they do not have any conflict of interest regarding the research objectives, procedures and results.
- 7.Yunusova Y, Green JR, Lindstrom MJ, Pattee GL, Zinman L (2013) Speech in ALS: longitudinal changes in lips and jaw movements and vowel acoustics. J Med Speech Lang Pathol 21(1):1–13Google Scholar
- 11.Bouchard KE, Conant DF, Anumanchipalli GK, Dichter B, Chaisanguanthum KS, Johnson K, Chang EF (2016) High-resolution, non-invasive imaging of upper vocal tract articulators compatible with human brain recordings. PLoS ONE 11(3):e0151327. https://doi.org/10.1371/journal.pone.0151327 CrossRefGoogle Scholar
- 12.NIST/SEMATECH e-Handbook of statistical methods. http://www.itl.nist.gov/div898/handbook/
- 13.López-de-Ipiña K, Alonso JB, Solé-Casals J, Barroso N, Henriquez P, Faundez-Zanuy M, Travieso CM, Ecay-Torres M, Martínez-Lage P, Eguiraun H (2015) On automatic diagnosis of Alzheimer’s disease based on spontaneous speech analysis and emotional temperature. Cognit Comput 7(1):44–55CrossRefGoogle Scholar
- 15.Deller JR, Proakis JG, Hansen JHL (1993) Discrete-time processing of speech signals. Prentice-Hall, Englewood CliffsGoogle Scholar
- 18.Sartucci F, Bocci T, Briscese L, Pecori C, Rossi C, Giannini F (2012) How to assess disease’s severity and monitor patients with amyotrophic lateral sclerosis: lessons from neurophysiology. In: Maurer M (ed) InTech Europe, pp 613–626Google Scholar
- 20.Proença J, Veiga A, Candeias S, Lemos J, Januário C, Perdigão F (2014) Characterizing Parkinson’s disease speech by acoustic and phonetic features. Lecture Notes Artif Intell 8775:24–35Google Scholar