Ensemble of classifiers for speech evaluation

TL;DR

This paper explores an ensemble of classifiers to evaluate speech quality in medical applications, using multiple metrics and expert assessments to improve classification accuracy.

Contribution

It introduces an ensemble approach combining five classifiers for speech assessment, demonstrating slight accuracy improvements over individual models.

Findings

Ensemble method slightly outperforms individual classifiers.

Multiple distance-based metrics are effective features.

Support vector machine and ensemble methods show promising results.

Abstract

The article describes an attempt to apply an ensemble of binary classifiers to solve the problem of speech assessment in medicine. A dataset was compiled based on quantitative and expert assessments of syllable pronunciation quality. Quantitative assessments of 7 selected metrics were used as features: dynamic time warp distance, Minkowski distance, correlation coefficient, longest common subsequence (LCSS), edit distance of real se-quence (EDR), edit distance with real penalty (ERP), and merge split (MSM). Expert as-sessment of pronunciation quality was used as a class label: class 1 means high-quality speech, class 0 means distorted. A comparison of training results was carried out for five classification methods: logistic regression (LR), support vector machine (SVM), naive Bayes (NB), decision trees (DT), and K-nearest neighbors (KNN). The results of using the mixture method to build an ensemble of classifiers are also presented. The use of an en-semble for the studied data sets allowed us to slightly increase the classification accuracy compared to the use of individual binary classifiers.