Implementing Gender-Dependent Vowel-Level Analysis for Boosting Speech-Based Depression Recognition

Abstract

Whilst studies on emotion recognition show that genderdependent analysis can improve emotion classification performance, the potential differences in the manifestation of depression between male and female speech have yet to be fully explored. This paper presents a qualitative analysis of phonetically aligned acoustic features to highlight differences in the manifestation of depression. Gender-dependent analysis with phonetically aligned gender-dependent features are used for speech-based depression recognition. The presented experimental study reveals gender differences in the effect of depression on vowel-level features. Considering the experimental study, we also show that a small set of knowledge-driven gender-dependent vowel-level features can outperform state-of-the-art turn-level acoustic features when performing a binary depressed speech recognition task. A combination of these preselected gender-dependent vowel-level features with turn-level standardised openSMILE features results in additional improvement for depression recognition.

Speech depression recognition based on attentional residual network

“…14). It is obvious from the figure that the accuracy of women is higher than that of men, which is consistent with the results of [24], indicating that gender can affect the classification performance of the model. The results obtained are compared with the results obtained using different machine learning algorithms.…”

AudVowelConsNet: A phoneme-level based deep CNN architecture for clinical depression diagnosis

“…Specifically, findings revealed a reduced frequency range in vowel production (Darby et al, 1984) and in the speech Vowel Space Area (VSA) (Scherer et al, 2015) in depression. Moreover, gender-dependent vowel level analysis was performed for boosting speech-based depression recognition (Vlasenko et al, 2017). Surprisingly, these studies ignored the speech consonant space.…”

Depression Screening from Voice Samples of Patients Affected by Parkinson’s Disease

“…According to Vlasenko et al [16], performance of depression detection was improved when the feature extraction process was conducted differently depending on gender. In a study by Helfer et al [17], distortions in formant trajectories of speech were shown to be a reliable indication of depression.…”