Alzheimer's disease preliminary screening method based on speech feature non-negative matrix decomposition

Abstract

The invention discloses an Alzheimer's disease preliminary screening method based on speech feature non-negative matrix decomposition. The Alzheimer's disease preliminary screening method includes thefollowing steps: extracting acoustic features including fundamental frequency, energy, harmonic-to-noise ratios, formants, glottal waves, linear prediction coefficients, and constant Q cepstrum coefficients, from speech samples of Alzheimer's patients and normal humans, and splicing the features into a feature matrix; using the non-negative matrix decomposition algorithm to decompose the featurematrix, and obtaining the dimensionality-reduced feature matrix; using the dimensionality-reduced feature matrix as an input, and training a support vector machine classifier; and inputting the dimensionality-reduced feature matrix of a test speech sample into the trained support vector machine classifier, and determining whether the test speech is speech of normal humans or speech of Alzheimer'spatients. The invention adopts non-negative matrix decomposition to perform dimensionality reduction transformation on high-dimensional input acoustic features, the dimensionality-reduced feature matrix has better discrimination, and the method can obtain more excellent effects in Alzheimer's disease preliminary screening.

Description

Technical field [0001] The invention relates to the technical field of audio signal processing and machine learning, in particular to a method for preliminary screening of Alzheimer's disease based on non-negative matrix decomposition of speech features. Background technique [0002] Alzheimer's disease is a progressive neurodegenerative disease with insidious onset. Due to extensive damage to the cerebral cortex and subcortical language network structure and its connection fibers, patients with Alzheimer’s disease have speech disorders, which have their own special patterns and evolution processes, involving oral expression, retelling, understanding, naming, reading and All aspects of writing. The speech disorder of Alzheimer's disease is positively correlated with the severity of dementia, which affects normal speech communication. [0003] As the condition of Alzheimer's disease worsens, the time and money costs required for rehabilitation of patients' speech function will als...

AI Technical Summary

Problems solved by technology

Although the evaluation is more objective, the above-mentioned instruments are relatively expensive, and some diagnostic methods are invasive, causing discomfort to patients, and Alzheimer's patients are not willing to cooperate with the diagnosis

Images