Validation of a Speech Database for Assessing College Students' Physical Competence under the Concept of Physical Literacy

This study developed a speech database for assessing one of the elements of physical literacy-physical competence. Thirty-one healthy and native Cantonese speakers were instructed to read a material aloud after various exercises. The speech database contained four types of speech, which were collected at rest and after three exercises of the Canadian Assessment of Physical Literacy 2nd Edition. To show the possibility of detecting each exercise state, a support vector machine (SVM) was trained on the acoustic features. Two speech feature sets, the extended Geneva Minimalistic Acoustic Parameter Set (eGeMAPS) and Computational Paralinguistics Challenge (ComParE), were utilized to perform speech signal processing. The results showed that the two stage four-class SVM were better than the stage one. The performances of both feature sets could achieve 70% accuracy (unweighted average recall (UAR)) in the three-class model after five-fold cross-validation. The UAR result of the resting and vigorous state on the two-class model running with the ComParE feature set was 97%, and the UAR of the resting and moderate state was 74%. This study introduced the process of constructing a speech database and a method that can achieve the short-time automatic classification of physical states. Future work on this corpus, including the prediction of the physical competence of young people, comparison of speech features with other age groups and further spectral analysis, are suggested.

Automated summary

This study developed a speech database to assess physical competence, one element of physical literacy. The database collected speech samples from 31 healthy Cantonese speakers in rest and after performing exercises. The study trained a support vector machine (SVM) on acoustic features using two speech feature sets, eGeMAPS and ComParE, for speech signal processing. The results showed that the four-class SVM outperformed the one-class SVM, achieving 70% accuracy in the three-class model. The study also suggested future work on predicting physical competence, comparing speech features across age groups, and conducting spectral analysis.