# Robust and Explainable Depression Identification from Speech Using Vowel-Based Ensemble Learning Approaches

arXiv: https://arxiv.org/abs/2410.18298 · HTML: https://mlsanity.com/paper/2410.18298/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 48 references that are in the map.
- First posted on arXiv 23 Oct 2024.

## Builds on (most cited first, 9 of 9)

- [GLaM: Efficient Scaling of Language Models with Mixture-of-Experts](https://mlsanity.com/paper/2112.06905/) (2021)
- [Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems](https://mlsanity.com/paper/1903.12394/) (2019)
- [AVEC 2016 - Depression, Mood, and Emotion Recognition Workshop and Challenge](https://mlsanity.com/paper/1605.01600/) (2016)
- [KeepAugment: A Simple Information-Preserving Data Augmentation Approach](https://mlsanity.com/paper/2011.11778/) (2020)
- [SpeechFormer: A Hierarchical Efficient Framework Incorporating the Characteristics of Speech](https://mlsanity.com/paper/2203.03812/) (2022)
- [Automatic Detection of Depression in Speech Using Ensemble Convolutional Neural Networks](https://mlsanity.com/paper/2402.02830/) (2024)
- [A knowledge-driven vowel-based approach of depression classification from speech using data augmentation](https://mlsanity.com/paper/2210.15261/) (2022)
- [Non-uniform Speaker Disentanglement For Depression Detection From Raw Speech Signals](https://mlsanity.com/paper/2306.01861/) (2023)
- [Toward Knowledge-Driven Speech-Based Models of Depression: Leveraging Spectrotemporal Variations in Speech Vowels](https://mlsanity.com/paper/2210.02527/) (2022)

## Built on by (most cited first, 2 of 2)

- [Clinically Inspired Symptom-Guided Depression Detection from Emotion-Aware Speech Representations](https://mlsanity.com/paper/2602.15578/) (2026)
- [Semi-Supervised Diseased Detection from Speech Dialogues with Multi-Level Data Modeling](https://mlsanity.com/paper/2601.04744/) (2026)

## Abstract (arXiv)

This study investigates explainable machine learning algorithms for identifying depression from speech. Grounded in evidence from speech production that depression affects motor control and vowel generation, pre-trained vowel-based embeddings, that integrate semantically meaningful linguistic units, are used. Following that, an ensemble learning approach decomposes the problem into constituent parts characterized by specific depression symptoms and severity levels. Two methods are explored: a "bottom-up" approach with 8 models predicting individual Patient Health Questionnaire-8 (PHQ-8) item scores, and a "top-down" approach using a Mixture of Experts (MoE) with a router module for assessing depression severity. Both methods depict performance comparable to state-of-the-art baselines, demonstrating robustness and reduced susceptibility to dataset mean/median values. System explainability benefits are discussed highlighting their potential to assist clinicians in depression diagnosis and screening.