Elderly Conversational Speech Corpus with Cognitive Impairment Test and Pilot Dementia Detection Experiment Using Acoustic Characteristics of Speech in Japanese Dialects

Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022), pages 1016–1022 Marseille, 20-25 June 2022 © European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0 1016 Elderly Conversational Speech Corpus with Cognitive Impairment Test and Pilot Dementia Detection Experiment Using Acoustic Characteristics of Speech in Japanese Dialects Meiko Fukuda1, Maina Umezawa2, Ryota Nishimura1, Yurie Iribe2, Kazumasa Yamamoto3, Norihide Kitaoka4 1Tokushima University, Tokushima, Japan 2Aichi Prefectural University, Aichi, Japan 3Chubu University, Department of Computer Science, Kasugai, Japan 4Toyohashi University of Technology, Toyohashi, Japan 1fukuda.meiko@tokushima-u.ac.jp Abstract There is a need for a simple method of detecting early signs of dementia which is not burdensome to patients, since early diagnosis and treatment can often slow the advance of the disease. Several studies have explored using only the acoustic and linguistic information of conversational speech as diagnostic material, with some success. To accelerate this research, we recorded natural conversations between 128 elderly people living in four different regions of Japan and interviewers, who also administered the Hasegawa’s Dementia Scale-Revised (HDS-R), a cognitive impairment test. Using our elderly speech corpus and dementia test results, we propose an SVM-based screening method which can detect dementia using the acoustic features of conversational speech even when regional dialects are present. We accomplish this by omitting some acoustic features, to limit the negative effect of differences between dialects. When using our proposed method, a dementia detection accuracy rate of about 91% was achieved for speakers from two regions. When speech from four regions was used in a second experiment, the discrimination rate fell to 76.6%, but this may have been due to using only sentence-level acoustic features in the second experiment, instead of sentence and phoneme-level features as in the previous experiment. This is an on-going research project, and additional investigation is needed to understand differences in the acoustic characteristics of phoneme units in the conversational speech collected from these four regions, to determine whether the removal of formants and other features can improve the dementia detection rate. Keywords: conversation, super-elderly, speech corpus, dementia 1. Introduction Although drugs are available to slow the progression of dementia, fundamental treatments are still under de- velopment, so it is important to diagnose individuals with the disease as early as possible. The World Health Organization (WHO) estimates that global rates of de- mentia will triple from current levels by 2050 (World Health Organization, 2021). In Japan, the number of elderly people with dementia is expected to reach 7 million by 2025, or about one in five people aged 65 or older. As a result, the Japanese government has made the early detection of dementia a national pri- ority(Ministry of Internal Affairs and Communication, Japan, 2015). The Mini-Mental State Examination (MMSE) is widely used internationally as a neuropsychological screening test for dementia, while Hasegawa’s Demen- tia Scale-Revised (HDS-R) (Imai and Hasegawa, 1994) is used more often in Japan and East Asia. These tests involve having subjects answer simple, verbal ques- tions and perform some task. These screening tests are convenient and high …

Content truncated to 500 words