Speech Processing Approach for Diagnosing Dementia in an Early Stage

Intra-subject analysis showed good specificity in classifying bipolar subjects and healthy controls across all F0 contour features, but the directions of most features were inconsistent across subjects.

“They noted that intra-subject analysis showed good specificity in classifying bipolar subjects and healthy controls across all contour features, but that directions of most were not consistent across different subjects.”

An automated method estimating the F0 contour over time with a moving window can serve as a proxy for mood changes in bipolar disorder.

“In this study, the authors propose an automated method for estimating the contour of F0 over time with a moving window approach as a proxy for mood changes.”

In certain studies, MMSE is used to calculate the baseline against which classifier performance will be measured.

“In certain studies, MMSE is used to calculate the baseline against which classifier performance will be measured [44, 70, 71].”

Very few reviewed papers report use of artificial neural networks, recurrent neural networks, multi-layer perceptron, or convolutional neural networks.

“As regards choice of machine learning methods, very few papers report the use of artificial neural networks [91, 95], recurrent neural networks [82], multi-layer perceptron [44, 67, 79, 80, 86], or convolutional neural networks [60, 85].”

Off-the-shelf ASR tools are not readily prepared for dementia research, and therefore some reviewed studies developed their own custom ASR systems.

“It is becoming increasingly obvious that off-the-shelf ASR tools are not readily prepared for dementia research, and therefore some reviewed studies developed their own custom ASR systems [44, 63].”

Cognitive scores, particularly MMSE, are available with many datasets, including the Pitt Corpus, but mostly remain unused except for diagnostic group assignments or rarely as baseline performance.

“Cognitive scores, particularly MMSE, are available with many datasets, including the most commonly used, Pitt Corpus. However, these scores mostly remain unused except for diagnostic group assignments, or more rarely, as baseline performance [44, 70, 71]”