Saved in:
Bibliographic Details
Main Authors: Feng, Kexin, Chaspari, Theodora
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.18298
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910664730083328
author Feng, Kexin
Chaspari, Theodora
author_facet Feng, Kexin
Chaspari, Theodora
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_18298
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Robust and Explainable Depression Identification from Speech Using Vowel-Based Ensemble Learning Approaches
Feng, Kexin
Chaspari, Theodora
Machine Learning
Computation and Language
Sound
Audio and Speech Processing
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.
title Robust and Explainable Depression Identification from Speech Using Vowel-Based Ensemble Learning Approaches
topic Machine Learning
Computation and Language
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2410.18298