Automated speech-based screening of depression using deep convolutional neural networks

Chlasta, Karol; Wołk, Krzysztof; Krejtz, Izabela

doi:10.1016/j.procs.2019.12.228

Cited by 48 publications

(20 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most widely used data classification algorithm is CNN. This can be seen from [16], wherein CNNs are used for speech-based screening of depression. In their work, researchers have taken real-time inputs from more than 2000 individuals, and then evaluated their mental state.…”

Section: Table 2 Algorithm Comparison On Mental Disease Classificationmentioning

confidence: 99%

“…Conditions like these when combined with advanced classifiers would result in a highly effective mental disorder classification system. [36][37][38][39][40][41][42] Auto Encoder [14] EEG for signal processing 83 CNN [14] EEG for signal processing 90 Ensemble classification [15] SVM, kNN and SSAE (Stacked Sparse Auto-Encoders) 91 SVM [16] MFCC, F0, F1, F2 85 LR [16] MFCC, F0, F1, F2 90 RLHE [17] SVM combined with RLHE 85 RF [18] Acoustic features 80 Elastic Nets [18] Acoustic features 85 CNN [18] Acoustic features 91 CNN [21] Heart rate variability 96 LSTM [23] XGBoost classifier & word2vec word embedding 95 DBS [24] CNN for OCD detection 91…”

Section: Table 3 Body Parameter Variation On the Mental State Of A Personmentioning

confidence: 99%

See 1 more Smart Citation

Analysing Mental Health Evaluation Techniques from a Statistical Perspective

Koushik¹,

Deepu²

2021

Atlantis Highlights in Computer Sciences

View full text Add to dashboard Cite

Mental wellbeing is an epitome of success for human beings. Recently, a lot of mental diseases that include anxiety, suicidal tendency, depression, bipolar disorder, obsessive compulsive disorder (OCD), etc. have deep-seated among all age groups. This is due to the fact that the social complexity has increased at work, in relationships, at home and in majorly all aspects of human life. Early detection of these problems can help in treating and if possible, eradicating this illness from a person's life. Researchers have proposed different techniques that can be put into action to effectively identify these diseases. These techniques utilize different activities of normal day-to-day human behaviour, like speech analysis, social media behavioural patterns, visual-activity pattern analysis, etc. Due to a large variety of available techniques, researchers find it difficult to standardize techniques for detection and evaluation of such diseases. Thus, in this paper we have performed an in-depth study about the state-of-the art methods to identify mental health issues. Readers will be able to get a bird's eye view of these methods and will be able to identify the best practices involved in mental health analysis. Moreover, this survey also recommends some possible improvements in the existing methods, in order to further improve the system's performance.

show abstract

Section: Table 2 Algorithm Comparison On Mental Disease Classificationmentioning

confidence: 99%

Section: Table 3 Body Parameter Variation On the Mental State Of A Personmentioning

confidence: 99%

Analysing Mental Health Evaluation Techniques from a Statistical Perspective

Koushik¹,

Deepu²

2021

Atlantis Highlights in Computer Sciences

View full text Add to dashboard Cite

show abstract

“…Discussion from few of those is as stated. [10]suggested the method of deep convolutional neural networks for analyzing depression in speech. Network architectures were developed and tested for providing the best classification results.…”

Section: Research Backgroundmentioning

confidence: 99%

Depression analysis of voice samples using machine learning

Sharma¹,

Singh²

2021

JUSST

View full text Add to dashboard Cite

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 pattern has been intruded by depression either do not avail proper medical attention or are too shy to appear in the masses for proper attention on their physical as well as condition. Our motivation here is to investigate through the phenomenon of depression and predict whether an individual is having symptoms of depression by accessing his/her voice sample. In order to establish a link between depression and voice features, we obtain a large data set and then train a model accordingly by applying machine learning methods on it. This model when given a voice sample can now predict, whether a particular subject is depressed or not, to a nearby accurate measure.

show abstract

“…It is also significantly faster than other residual block networks (ResNet-50, ResNet-101) without compromising the classification accuracy [24]. ResNet18 has shown good performance in comparison with other pre-trained CNN models in speech classification tasks such as, for example, intoxication detection [31], depression detection [32], and speech command recognition [33]. In the current study, the original last fully connected layer of ResNet-18, the Softmax layer, and the output layer were modified to have the number of class outputs required by a given experiment.…”

Section: ) Cnn Modelmentioning

confidence: 99%