Skip to main content

Table 4 Incoherence (clinician-rated) and correlations (p<0.05) with speech variables, ranked by correlation coefficient (Spearman’s |ρ|)

From: Correlating natural language processing and automated speech analysis with clinician assessment to quantify speech-language changes in mild cognitive impairment and Alzheimer’s dementia

Variable type

Variable description

ρ

F1

F2

Syntactic

Use of past tense verb phrases with noun phrases

0.51

0.69

 

Lexical

Average age of acquisition score of all words

0.47

 

− 0.64

Acoustic

Speech rate

− 0.47

  

Acoustic

Average word duration

0.47

0.64

 

Lexical

Average age of acquisition score of nouns

0.46

 

− 0.65

Lexical

Average valence score of nouns

− 0.43

 

0.79

Acoustic

Skewness of the second derivative of the 4th MFCC

− 0.42

− 0.87

 

Semantic

Proportion of subject words used

− 0.42

  

Syntactic

Use of 3rd person singular present verb phrases with prepositional phrases

− 0.41

  

Acoustic

Kurtosis of the second derivative of the 4th MFCC

0.41

0.98

 

Syntactic

Use of prepositional phrases with noun phrases

− 0.40

  

Acoustic

Skewness of the second derivative of the log energy

− 0.39

− 0.96

 

Lexical

Use of comparative adjectives

0.38

  

Acoustic

Kurtosis of the second derivative of the log energy

0.38

0.95

 

Semantic

Semantic similarity of description to picture content (max cosine distance, 300-dim word vectors)

0.38

  

Semantic

Average valence score of all words

− 0.37

 

0.82

Syntactic

Use of singular present verb phrases with prepositional phrases

− 0.37

  

Syntactic

Use of verb phrases with noun phrases

0.37

  

Semantic

Proportion of subjects in picture described

− 0.37

  

Lexical

Average arousal score of nouns

− 0.36

  
  1. Columns F1 and F2 indicate which variables were assigned to each factor, and the factor loading scores. Variables that do not have values in columns F1 and F2 are correlated with incoherence but were not included in a factor based on the exploratory factor analysis