Using speech recognition technology to investigate the association between timing-related speech features and depression severity

Yamamoto, Mao; Takamiya, Akihiro; Sawada, Kyosuke; Yoshimura, Michitaka; Kitazawa, Momoko; Liang, Kuo Ching; Fujita, Takanori; Mimura, Masaru; Kishimoto, Toshifumi

doi:10.1371/journal.pone.0238726

Cited by 43 publications

(30 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A study using different languages such as English [31] and Japanese [32] have shown that timingbased feature is a promising biomarker for depression speech. Initial studies on pauses and silence found that pause time was longer for depressed patients than in healthy speech.…”

Section: Comparison Of Classifiers Performance On Depressed Speech Classificationsmentioning

confidence: 99%

Comparison of classifiers using robust features for depression detection on Bahasa Malaysia speech

Hashim

Basri

Ezzi

et al. 2022

IJ-AI

View full text Add to dashboard Cite

Early detection of depression allows rapid intervention and reduce the escalation of the disorder. Conventional method requires patient to seek diagnosis and treatment by visiting a trained clinician. Bio-sensors technology such as automatic depression detection using speech can be used to assist early diagnosis for detecting remotely those who are at risk. In this research, we focus on detecting depression using Bahasa Malaysia language using speech signals that are recorded remotely via subject’s personal mobile devices. Speech recordings from a total of 43 depressed subjects and 47 healthy subjects were gathered via online platform with diagnosis validation according to the Malay beck depression inventory II (Malay BDI-II), patient health questionnaire (PHQ-9) and subject’s declaration of major depressive disorder (MDD) diagnosis by a trained clinician. Classifier models were compared using time-based and spectrum-based microphone independent feature set with hyperparameter tuning. Random forest performed best for male reading speech with 73% accuracy while support vector machine performed best on both male spontaneous speech and female reading speech with 74% and 73% accuracy, respectively. Automatic depression detection on Bahasa Malaysia language has shown to be promising using machine learning and microphone independent features but larger database is necessary for further validation and improving performance.

show abstract

Section: Comparison Of Classifiers Performance On Depressed Speech Classificationsmentioning

confidence: 99%

Comparison of classifiers using robust features for depression detection on Bahasa Malaysia speech

Hashim

Basri

Ezzi

et al. 2022

IJ-AI

View full text Add to dashboard Cite

show abstract

“…We have reported that the timing related speech features can reflect the severity of depression. Speech rate, pause time, and response time showed significant associations with the total score of Hamilton Depression Rating Scale ( 15 , 16 ). We have also reported that body movement captured by infrared sensor can be reflective of depression severity ( 15 , 17 ).…”

Section: Introductionmentioning

confidence: 99%

Unobtrusive Sensing Technology for Quantifying Stress and Well-Being Using Pulse, Speech, Body Motion, and Electrodermal Data in a Workplace Setting: Study Concept and Design

et al. 2021

Self Cite

View full text Add to dashboard Cite

Introduction: Mental disorders are a leading cause of disability worldwide. Depression has a significant impact in the field of occupational health because it is particularly prevalent during working age. On the other hand, there are a growing number of studies on the relationship between “well-being” and employee productivity. To promote healthy and productive workplaces, this study aims to develop a technique to quantify stress and well-being in a way that does not disturb the workplace.Methods and analysis: This is a single-arm prospective observational study. The target population is adult (>20 years old) workers at companies that often engage in desk work; specifically, a person who sits in front of a computer for at least half their work hours. The following data will be collected: (a) participants' background characteristics; (b) participants' biological data during the 4-week observation period using sensing devices such as a camera built into the computer (pulse wave data extracted from the facial video images), a microphone built into their work computer (voice data), and a wristband-type wearable device (electrodermal activity data, body motion data, and body temperature); (c) stress, well-being, and depression rating scale assessment data. The analysis workflow is as follows: (1) primary analysis, comprised of using software to digitalize participants' vital information; (2) secondary analysis, comprised of examining the relationship between the quantified vital data from (1), stress, well-being, and depression; (3) tertiary analysis, comprised of generating machine learning algorithms to estimate stress, well-being, and degree of depression in relation to each set of vital data as well as multimodal vital data.Discussion: This study will evaluate digital phenotype regarding stress and well-being of white-collar workers over a 4-week period using persistently obtainable biomarkers such as heart rate, acoustic characteristics, body motion, and electrodermal activity. Eventually, this study will lead to the development of a machine learning algorithm to determine people's optimal levels of stress and well-being.Ethics and dissemination: Collected data and study results will be disseminated widely through conference presentations, journal publications, and/or mass media. The summarized results of our overall analysis will be supplied to participants.Registration: UMIN000036814

show abstract

“…Speech has great potential to be a source of such phenotypes and to provide unique preventative and predictive information about depression [5,6,7,8]. However, current research in this space is not without its limitations.…”

Section: Introductionmentioning

confidence: 99%

Speech and the n-Back task as a lens into depression. How combining both may allow us to isolate different core symptoms of depression

Fara¹,

Goria²,

Molimpakis³

et al. 2022

Preprint

View full text Add to dashboard Cite

Embedded in any speech signal is a rich combination of cognitive, neuromuscular and physiological information. This richness makes speech a powerful signal in relation to a range of different health conditions, including major depressive disorders (MDD). One pivotal issue in speech-depression research is the assumption that depressive severity is the dominant measurable effect. However, given the heterogeneous clinical profile of MDD, it may actually be the case that speech alterations are more strongly associated with subsets of key depression symptoms. This paper presents strong evidence in support of this argument. First, we present a novel large, cross-sectional, multimodal dataset collected at Thymia. We then present a set of machine learning experiments that demonstrate that combining speech with features from an n-Back working memory assessment improves classifier performance when predicting the popular eight-item Patient Health Questionnaire depression scale (PHQ-8). Finally, we present a set of experiments that highlight the association between different speech and n-Back markers at the PHQ-8 item level. Specifically, we observe that somatic and psychomotor symptoms are more strongly associated with n-Back performance scores, whilst the other items: anhedonia, depressed mood, change in appetite, feelings of worthlessness and trouble concentrating are more strongly associated with speech changes.

show abstract

Using speech recognition technology to investigate the association between timing-related speech features and depression severity

Cited by 43 publications

References 33 publications

Comparison of classifiers using robust features for depression detection on Bahasa Malaysia speech

Comparison of classifiers using robust features for depression detection on Bahasa Malaysia speech

Unobtrusive Sensing Technology for Quantifying Stress and Well-Being Using Pulse, Speech, Body Motion, and Electrodermal Data in a Workplace Setting: Study Concept and Design

Speech and the n-Back task as a lens into depression. How combining both may allow us to isolate different core symptoms of depression

Contact Info

Product

Resources

About