Acoustic Markers Associated with Impairment in Language Processing in Alzheimer's Disease

Abstract

This study broaches in a novel way the analysis of cognitive impairment characteristic of the early stages of Alzheimer's Disease (AD). Specifically, we attempt to determine the acoustic speech parameters that are sensitive to the onset of the disease, and their association with the language deficit characteristic of AD. Speech analysis was carried out on 21 elderly patients with AD using Praat software, which analyzes the acoustic components of speech. The data obtained were subjected to stepwise regression, using the overall scores obtained in the test as the criterion variable, and the scores on the frequency, amplitude and periodicity variables as predictors of performance. We found that the percentage of voiceless segments explains a significant portion of the variance in the overall scores obtained in the neuropsychological test. This component seems to be related mainly to the patient's ability in phonological fluency. This finding could permit the creation of a diagnostic test for AD through analysis of the acoustic speech parameters at very low cost in terms of both time and resources.

Automatic speech analysis for the assessment of patients with predementia and Alzheimer's disease

“…These features presumably covered the task-specific manifestation of dementia in the speech data. Some were similar to features described in previous studies [2], [20], [35], [36], [37] and others were novel. Because of the developing language-independent technology, speech recognition was not included, and only nonverbal features were targeted.…”

“…Our results are in line with the findings from Gayraud et al [42], who showed that patients with AD differ from controls in their process of discourse production, displaying more frequent silent pauses outside the syntactic boundaries, which might be a marker of planning difficulties. Meilan et al [20] found that the increase in voiceless segments in a patient's speech is a sign that explains more than 34% of the variance in scores obtained for a specific language and memory test. Thus, this increase could be related to AD and to some extent to the cognitive impairments associated with it.…”

Speech in Alzheimer's Disease: Can Temporal and Acoustic Parameters Discriminate Dementia?

“…These seem to also be altered due to disease as reported by ourselves and other authors using different methodology [13,21,24]. Recently, Meilán et al [22] have found that an increase in the percentage of voiceless segments in AD patients' speech explains more than 34% of the variance in the scores in a specific language and memory test. Roark et al [23], in a task where the participants were asked to re-tell a story (Wechsler Logical Memory Scale) immediately after it had been told to them, found that the standardised pause rate, phonation rate, and many linguistic complexity measures were useful in discriminating between healthy elderly participants and participants with mild cognitive impairment.…”

“…Subtle speech alterations were revealed in a recent study indicating the difficulties in expression (e.g. percentage of voiceless segments) shown by patients with AD in the early stages of the disease [21,22] and the difficulties in speech duration (e.g. mean duration of pauses, standardized phonation time, and verbal rate) observed in patients with mild cognitive impairment [23].…”

On the Selection of Non-Invasive Methods Based on Speech Analysis Oriented to Automatic Alzheimer Disease Diagnosis

“…Spoken language is the most spontaneous, natural, intuitive and efficient method of communication among people. Therefore, the analysis by automated methods of Spontaneous Speech (SS) or Automatic Speech Analysis (ASSA) which is the freer and more natural expression of communication, possibly combined with other methodologies, has the potential to become a useful non-invasive method for early AD diagnosis [15,20–24]. …”