Possibilities of Recognizing Depression with Convolutional Networks Applied in Correlation Structure

In the present study, we attempt to estimate the severity of depression using a Convolutional Neural Network (CNN). The method is special because an auto- and cross-correlation structure has been crafted rather than using an actual image for the input of the network. The importance to investigate the possibility of this research is that depression has become one of the leading mental disorders in the world. With its appearance, it can significantly reduce an individual's quality of life even at an early stage, and in severe cases, it may threaten with suicide. It is therefore important that the disorder be recognized as early as possible. Furthermore, it is also important to determine the disorder severity of the individual, so that a treatment order can be established. During the examination, speech acoustic features were obtained from recordings. Among the features, MFCC coefficients and formant frequencies were used based on preliminary studies. From its subsets, correlation structure was created. We applied this quadratic structure to the input of a convolutional network. Two models were crafted: single and double input versions. Altogether, the lowest RMSE value (10.797) was achieved using the two features, which has a moderate strength correlation of 0.61 (between estimated and original).

show abstract

“…MFCC features were used at a displacement rate of 8 and formants at a displacement rate of 1 based on [24] preliminary study.…”

Section: Implementation Of Evaluationmentioning

confidence: 99%

Severity Estimation of Depression Using Convolutional Neural Network

Jenei

Kiss

2021

Period. Polytech. Elec. Eng. Comp. Sci.

View full text Add to dashboard Cite

show abstract

“…Prior studies made use of the HDSDb but with fewer samples, e.g. : CNNs and a speech correlation structure were used in [95] (accuracy of 84.1% with 188 samples). Also, the use of a special feature acoustic parameter selection approach in [109] (8.10 of RMSE with 127 samples).…”

Section: Related Workmentioning

confidence: 99%

Adaptation of Speaker and Speech Recognition Methods for the Automatic Screening of Speech Disorders using Machine Learning

Egas-López

View full text Add to dashboard Cite

Jelen doktori értekezés olyan módszereket mutat be, amelyek bizonyos betegségekben vagy egészségi állapotban szenvedő egyének nemverbális kommunikációjának kiaknázását célozzák azok automatikus szűrésére. Konkrétabban, a nemverbális kommunikáció egyik pillérét, a paralingvisztikát alkalmaztuk olyan technikák feltárására, amelyek felhasználhatók az alanyok beszédének modellezésére. A paralingvisztika a kommunikáció egy nem lexikális összetevője, amely az intonáción, a hangmagasságon, a beszéd sebességén stb. alapszik, és amely automatikusan feldolgozható és elemezhető. Ezt Computational Paralinguistics-nak hívják, amely úgy definiálható, mint a beszélő beszédében lévő nemverbális látens minták számítási algoritmusok segítségével történő modellezése. A gépi tanulás segítségével modelleket mutatunk be mind a paralingvisztikai, mind az orvosi célú beszédelemzés különböző forgatókönyveiből, amelyek alkalmasak egy adott betegséggel (például az Alzheimer-kór, Parkinson-kór, depresszió) élő alanyok egészségi állapotának automatikus becslésére.

show abstract