Can a Machine Distinguish High and Low Amount of Social Creak in Speech?

TL;DR

This study demonstrates that machine learning models can effectively classify high versus low social creak in speech, providing a potential tool to assist sociolinguistic and vocological research.

Contribution

The paper introduces ML-based methods to automatically distinguish social creak levels in speech, achieving over 70% accuracy, which advances automated analysis in this area.

Findings

Best accuracy of 71.1% with Adaboost and mel-spectrogram features

Decision tree classifier with MFCC features also performed well

ML can assist in reducing laborious perceptual assessments

Abstract

Objectives: ncreased prevalence of social creak particularly among female speakers has been reported in several studies. The study of social creak has been previously conducted by combining perceptual evaluation of speech with conventional acoustical parameters such as the harmonic-to-noise ratio and cepstral peak prominence. In the current study, machine learning (ML) was used to automatically distinguish speech of low amount of social creak from speech of high amount of social creak. Methods: The amount of creak in continuous speech samples produced in Finnish by 90 female speakers was first perceptually assessed by two voice specialists. Based on their assessments, the speech samples were divided into two categories (low $vs$. high amount of creak). Using the speech signals and their creak labels, seven different ML models were trained. Three spectral representations were used as feature for each model. Results: The results show that the best performance (accuracy of 71.1\%) was obtained by the following two systems: an Adaboost classifier using the mel-spectrogram feature and a decision tree classifier using the mel-frequency cepstral coefficient feature. Conclusions: The study of social creak is becoming increasingly popular in sociolinguistic and vocological research. The conventional human perceptual assessment of the amount of creak is laborious and therefore ML technology could be used to assist researchers studying social creak. The classification systems reported in this study could be considered as baselines in future ML-based studies on social creak.