Speech Emotion Analysis Using Machine Learning for Depression Recognition: a Review

EasyChair Preprint 8042, version 2

Abstract

Depression is a psychiatric disorder which can affect individual's physical health and wellbeing. Untreated depression can disrupt a person's quality of life and results in a cascade of further symptoms. Current diagnostic approaches are confined to clinical intervention. Hence, this system is proposed to detect depression at an early stage and also to offer help while taking clinical management decisions during treatment.

Communication is essential for conveying our thoughts and ideas to others. Machine Learning is quickly progressing in its ability to bring more sophisticated systems into everyday use. Intelligent systems are interactive and operate with little user effort, relying primarily on voice input. The purpose of this article is to show various algorithms for detecting speech emotions in order to recognize depression using machine learning.

Keyphrases: DAIC-WOZ, LSTM, RAVEDESS, SVM

@booklet{EasyChair:8042,
  author    = {S Bhavya and Royson Clausit Dmello and Ashish Nayak and Sakshi S Bangera},
  title     = {Speech Emotion Analysis Using Machine Learning for Depression Recognition: a Review},
  howpublished = {EasyChair Preprint 8042},
  year      = {EasyChair, 2022}}