AudVowelConsNet: A Phoneme-Level Based Deep CNN Architecture for Clinical Depression Diagnosis

TL;DR

This paper introduces a deep learning system that analyzes phoneme-level speech features, specifically vowels and consonants, to improve automatic depression diagnosis from speech data.

Contribution

It proposes and compares three spectrogram-based deep neural network architectures focusing on phoneme units, demonstrating superior performance through fusion of vowel and consonant features.

Findings

Consonant-based features outperform vowel-based features in depression recognition.

Fusion of vowel and consonant features significantly improves accuracy.

The proposed approach outperforms existing deep learning methods on the DAIC-WOZ dataset.

Abstract

Depression is a common and serious mood disorder that negatively affects the patient's capacity of functioning normally in daily tasks. Speech is proven to be a vigorous tool in depression diagnosis. Research in psychiatry concentrated on performing fine-grained analysis on word-level speech components contributing to the manifestation of depression in speech and revealed significant variations at the phoneme-level in depressed speech. On the other hand, research in Machine Learning-based automatic recognition of depression from speech focused on the exploration of various acoustic features for the detection of depression and its severity level. Few have focused on incorporating phoneme-level speech components in automatic assessment systems. In this paper, we propose an Artificial Intelligence (AI) based application for clinical depression recognition and assessment from speech. We investigate the acoustic characteristics of phoneme units, specifically vowels and consonants for depression recognition via Deep Learning. We present and compare three spectrogram-based Deep Neural Network architectures, trained on phoneme consonant and vowel units and their fusion respectively. Our experiments show that the deep learned consonant-based acoustic characteristics lead to better recognition results than vowel-based ones. The fusion of vowel and consonant speech characteristics through a deep network significantly outperforms the single space networks as well as the state-of-art deep learning approaches on the DAIC-WOZ database.