Speech rhythm alterations in Spanish-speaking individuals with Alzheimer's disease

• Published in: Aging, Neuropsychology, and Cognition Vol. 24; no. 4; pp. 418 - 434
• Main Authors: Martínez-Sánchez, Francisco, Meilán, Juan J. G., Vera-Ferrandiz, Juan Antonio, Carro, Juan, Pujante-Valverde, Isabel M., Ivanova, Olga, Carcavilla, Nuria
• Format: Journal Article
• Language: English
• Published: United States Routledge 04.07.2017
• Subjects: Aged; Algorithms; Alzheimer Disease - diagnosis; Alzheimer Disease - physiopathology; Alzheimer's disease; Diagnosis, Computer-Assisted; Educational Status; Female; Humans; Language; Male; Neuropsychological Tests; Pairwise variability index; Periodicity; Reading; Rhythm metrics; Sensitivity and Specificity; Signal Processing, Computer-Assisted; Speech; Speech Disorders - diagnosis; Speech Disorders - etiology; Speech Disorders - physiopathology; Speech Production Measurement; Speech rhythm; Voice-based diagnosis; Voice-based diagnosis; Alzheimer’s disease; Rhythm metrics; Speech rhythm; Pairwise variability index
• ISSN: 1382-5585; 1744-4128
• DOI: 10.1080/13825585.2016.1220487

Rhythm is the speech property related to the temporal organization of sounds. Considerable evidence is now available for suggesting that dementia of Alzheimer's type is associated with impairments in speech rhythm. The aim of this study is to assess the use of an automatic computerized system for measuring speech rhythm characteristics in an oral reading task performed by 45 patients with Alzheimer's disease (AD) compared with those same characteristics among 82 healthy older adults without a diagnosis of dementia, and matched by age, sex and cultural background. Ranges of rhythmic-metric and clinical measurements were applied. The results show rhythmic differences between the groups, with higher variability of syllabic intervals in AD patients. Signal processing algorithms applied to oral reading recordings prove to be capable of differentiating between AD patients and older adults without dementia with an accuracy of 87% (specificity 81.7%, sensitivity 82.2%), based on the standard deviation of the duration of syllabic intervals. Experimental results show that the syllabic variability measurements extracted from the speech signal can be used to distinguish between older adults without a diagnosis of dementia and those with AD, and may be useful as a tool for the objective study and quantification of speech deficits in AD.