Predicting Individual Depression Symptoms from Acoustic Features During Speech

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rodriguez, Sebastian, Dumpala, Sri Harsha, Dikaios, Katerina, Rempel, Sheri, Uher, Rudolf, Oore, Sageev
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914846736384000
author Rodriguez, Sebastian
Dumpala, Sri Harsha
Dikaios, Katerina
Rempel, Sheri
Uher, Rudolf
Oore, Sageev
author_facet Rodriguez, Sebastian
Dumpala, Sri Harsha
Dikaios, Katerina
Rempel, Sheri
Uher, Rudolf
Oore, Sageev
contents Current automatic depression detection systems provide predictions directly without relying on the individual symptoms/items of depression as denoted in the clinical depression rating scales. In contrast, clinicians assess each item in the depression rating scale in a clinical setting, thus implicitly providing a more detailed rationale for a depression diagnosis. In this work, we make a first step towards using the acoustic features of speech to predict individual items of the depression rating scale before obtaining the final depression prediction. For this, we use convolutional (CNN) and recurrent (long short-term memory (LSTM)) neural networks. We consider different approaches to learning the temporal context of speech. Further, we analyze two variants of voting schemes for individual item prediction and depression detection. We also include an animated visualization that shows an example of item prediction over time as the speech progresses.
format Preprint
id arxiv_https___arxiv_org_abs_2406_16000
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Predicting Individual Depression Symptoms from Acoustic Features During Speech
Rodriguez, Sebastian
Dumpala, Sri Harsha
Dikaios, Katerina
Rempel, Sheri
Uher, Rudolf
Oore, Sageev
Sound
Artificial Intelligence
Machine Learning
Audio and Speech Processing
Current automatic depression detection systems provide predictions directly without relying on the individual symptoms/items of depression as denoted in the clinical depression rating scales. In contrast, clinicians assess each item in the depression rating scale in a clinical setting, thus implicitly providing a more detailed rationale for a depression diagnosis. In this work, we make a first step towards using the acoustic features of speech to predict individual items of the depression rating scale before obtaining the final depression prediction. For this, we use convolutional (CNN) and recurrent (long short-term memory (LSTM)) neural networks. We consider different approaches to learning the temporal context of speech. Further, we analyze two variants of voting schemes for individual item prediction and depression detection. We also include an animated visualization that shows an example of item prediction over time as the speech progresses.
title Predicting Individual Depression Symptoms from Acoustic Features During Speech
topic Sound
Artificial Intelligence
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2406.16000