Depression Detection from Speech

2022

Depression is the most common psychological disorder and is considered as a leading cause of disability and suicide worldwide. An automated system capable of detecting signs of depression in human speech can contribute to ensuring timely and effective mental health care for individuals suffering from the disorder. Developing such automated system requires accurate machine learning models, capable of capturing signs of depression. However, state-of-the-art models based on deep acoustic representations require abundant data, meticulous selection of features, and rigorous training; the procedure involves enormous computational resources. In this work, we explore the effectiveness of two different acoustic feature groupsconventional hand-curated and deep representation features, for predicting the severity of depression from speech. We explore the relevance of possible contributing factors to the models' performance, including gender of the individual, severity of the disorder, content and length of speech. Our findings suggest that models trained on conventional acoustic features perform equally well or better than the ones trained on deep representation features at significantly lower computational cost, irrespective of other factors, e.g. content and length of speech, gender of the speaker and severity of the disorder. This makes such models a better fit for deployment where availability of computational resources is restricted, such as real time depression monitoring applications in smart devices.

International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2019

Depression is a common and serious medical illness which affects the way how we think, feel and act. Although harmless in its initial stages, it can cause serious problems if detected at a later stage. Due to advancements in technology, it is now possible to detect signs of depression. Different implementation of machine learning algorithms has been worked upon to detect factors causing depression. It is found that speech of a person is dramatically affected and various vocal features are used to classify depression.

Journal of Medical Internet Research

Background Automatic diagnosis of depression based on speech can complement mental health treatment methods in the future. Previous studies have reported that acoustic properties can be used to identify depression. However, few studies have attempted a large-scale differential diagnosis of patients with depressive disorders using acoustic characteristics of non-English speakers. Objective This study proposes a framework for automatic depression detection using large-scale acoustic characteristics based on the Korean language. Methods We recruited 153 patients who met the criteria for major depressive disorder and 165 healthy controls without current or past mental illness. Participants' voices were recorded on a smartphone while performing the task of reading predefined text-based sentences. Three approaches were evaluated and compared to detect depression using data sets with text-dependent read speech tasks: conventional machine learning models based on acoustic features, a pr...

International Journal for Research in Applied Science & Engineering Technology (IJRASET), 2022

Clinical depression is a type of soft biometric trait that can be used to characterize a person. Because of its importance in a variety of legal situations, this mood illness can be included in forensic psychological evaluations. In recent years, research into the automatic detection of depression based on medical data has yielded a variety of algorithmic approaches and auditory indicators. Machine learning algorithms have recently been used successfully in a variety of applications. Automatic depression recognition-the recognition of expressions linked with sad behavior is one of the most important applications. Modern algorithms for detecting depression usually look at both geographical and temporal data separately. This research introduces a novel machine learning strategy for accurately representing face information associated to depressive behaviors from real-world medical data. Our suggested architecture outperforms state-of-the-art algorithms in automatic depression recognition, according to results from two benchmark datasets.

Journal of University of Shanghai for Science and Technology, 2021

Depression is seen as an emerging mental challenge in the lives of various people. Nowadays it is also becoming one of the major reasons for mental disability across the world. Depression has manifested itself as a silent killer and according to statistics it has affected more than 300 million people in United States of America majorly affecting individuals in the age group of 15 to 44 yrs. According to a study by World Health Organization, the effects of depression have been dangerous in life, it is seen causing threatening diseases like cancer, diabetic issues or even heart disease. However, the problem that mainly is associated with the disease of depression is that it is not treated as a disease. Where the common understanding of the word “Disease” is any medical ailment that require doctor’s attention or quick medical response, depression on the other hand, even after qualifying as a disease is hidden in societal barriers to appear for a proper treatment. People whose lifestyle...

2021

BACKGROUND In the future, automatic diagnosis of depression based on speech could complement mental health treatment methods. Previous studies have reported that acoustic properties can be used to recognize depression, including mel-frequency cepstrum coefficients (MFCCs) applied to speech recognition. However, there are few studies in which these characteristics allow differential diagnosis of patients with depressive disorder. OBJECTIVE This paper proposes a framework to help with automatic depression detection in a mobile environment where speech data can be easily obtained. Specifically, we recorded speech data by performing a predefined text-based speech reading task on mobile, investigated whether the recorded data can screen for depression, and proposed a deep learning-based framework that helps in automatic depression detection. METHODS We recruited 125 patients who met the criteria for major depressive disorder (MDD) and 113 healthy controls without current or past mental i...

2020

Depression is among the foremost common and harmful mental health issues that are rapidly affecting lives worldwide having an enormous impact on well-being and functionality, and important personal, family, and societal effects. Depression not only affects emotional state, but also the physical state of the person. Lacking objective clinical depression assessment methods is the key reason that several depressive patients can’t be treated properly. Automatic depression assessment supported visual signals could be a rapidly grown research domain. Human being's cognitive system is often simulated by artificially intelligent systems. Much recent research has shown a relationship between mood changes and changed emotional attention. The analysis of audio features can be an important tool to help in depression identification and monitoring over the course of depressive disorder and recovery. In such a low mood, the voice of human beings appears different from the ones in normal states...

2020

There is a sample imbalance in the dataset, as there are more number of non-depressed patients in the dataset. To remove this sample imbalance, we introduce random sampling before the model training.

Cognitive Computation, 2021

Depression is one of the most common mental health issues. (It affects more than 4% of the world’s population, according to recent estimates.) This article shows that the joint analysis of linguistic and acoustic aspects of speech allows one to discriminate between depressed and nondepressed speakers with an accuracy above 80%. The approach used in the work is based on networks designed for sequence modeling (bidirectional Long-Short Term Memory networks) and multimodal analysis methodologies (late fusion, joint representation and gated multimodal units). The experiments were performed over a corpus of 59 interviews (roughly 4 hours of material) involving 29 individuals diagnosed with depression and 30 control participants. In addition to an accuracy of 80%, the results show that multimodal approaches perform better than unimodal ones owing to people’s tendency to manifest their condition through one modality only, a source of diversity across unimodal approaches. In addition, the e...

Pattern Recognition. ICPR International Workshops and Challenges, 2021

Intelligent monitoring systems and affective computing applications have emerged in recent years to enhance healthcare. Examples of these applications include assessment of affective states such as Major Depressive Disorder (MDD). MDD describes the constant expression of certain emotions: negative emotions (low Valence) and lack of interest (low Arousal). High-performing intelligent systems would enhance MDD diagnosis in its early stages. In this paper, we present a new deep neural network architecture, called EmoAudioNet, for emotion and depression recognition from speech. Deep EmoAudioNet learns from the timefrequency representation of the audio signal and the visual representation of its spectrum of frequencies. Our model shows very promising results in predicting affect and depression. It works similarly or outperforms the state-of-the-art methods according to several evaluation metrics on RECOLA and on DAIC-WOZ datasets in predicting arousal, valence, and depression.