On the analysis of speech and disfluencies for automatic detection of Mild Cognitive Impairment

Abstract

Alzheimer's disease is characterized by a progressive and irreversible cognitive deterioration. In a previous stage, the socalled Mild Cognitive Impairment or cognitive loss appears. Nevertheless, this previous stage does not seem sufficiently severe to interfere in independent abilities of daily life, so it is usually diagnosed inappropriately. Thus, its detection is a crucial challenge to be addressed by medical specialists. This paper presents a novel proposal for such early diagnosis based on automatic analysis of speech and disfluencies, and Deep Learning methodologies. The proposed tools could be useful for supporting Mild Cognitive Impairment diagnosis. The Deep Learning approach includes Convolutional Neural Networks and nonlinear multifeature modeling. Additionally, an automatic hybrid methodology is used in order to select the most relevant features by means of nonparametric Mann-Whitney U test and Support Vector Machine Attribute evaluation.

Ten Years of Research on Automatic Voice and Speech Analysis of People With Alzheimer's Disease and Mild Cognitive Impairment: A Systematic Review Article

“…In the predictive studies on AD, the results are variable, and most of them range from 80 to 95% accuracy regardless of the type of task. In the case of MCI, the highest accuracy (95%) is achieved through a semantic verbal fluency task (López-de-Ipiña et al, 2018a ), which is in marked contrast to the range normally found using other linguistic tasks (80–85%). However, it is not possible to affirm that semantic verbal fluency tasks are the most effective ones, as some of those studies also used acoustic features extracted during the execution of the task.…”

“…Furthermore, they could differentiate people with MCI from those with AD with 80% accuracy. López-de-Ipiña et al ( 2018a , b ) also used combinations of features with 73–95% accuracy for MCI. By combining prosodic features produced while repeating numbers backwards, Kato et al ( 2018 ) classified people with MCI with 76.4% accuracy.…”

Fluency Changes due to Sports-Related Concussion

“…This study examined speech error patterns in Division I college athletes in the acute time period following a sports-related concussion with a prediction that a head injury may affect cognitive-linguistic functions contributing to fluent speech output, thereby impacting the extent of speech errors that occur (López-de-Ipiña et al, 2020). Baseline measures of speech disfluency in connected speech were compared to performance within 48 hours after symptoms appeared (up to 4 days following a concussion).…”

Speech pause distribution as an early marker for Alzheimer’s disease

“…Filled pauses were thus standardized place-holders that were not lexicalized such as "uhm" or "erm", as opposing filler expressions such as "bueno" ("well") or the strategic lengthening of conjuctions, which were labelled as fillers and included in the disfluency tally. While some authors consider these vocalized pauses disfluencies [108,109] or fillers [110,111,112], most studies in the speech and dementia literature count them as filled pauses when explicitly described [69,61,113]. The lower temporal threshold for pause segmentation was set at 50 milliseconds.…”