Simple Search:

Classifications of clinical depression detection using acoustic measures in Malay speakers


Citation

Azam, Huda and Nik Hashim, Nik Nur Wahidah and Sediono, Wahju and Mukhtar, Firdaus and Ibrahim, Normala and Syed Mokhtar, Syarifah Suziah and Abdul Aziz, Salina (2016) Classifications of clinical depression detection using acoustic measures in Malay speakers. In: 2016 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES), 4-8 Dec. 2016, Kuala Lumpur, Malaysia. (pp. 606-610).

Abstract / Synopsis

Objective screening mechanism using paralinguistic cues to enhance current diagnostic on detecting depression is desirable, which resulted in the rise of research on this area. However, to date, there has been no research done using dataset of Malay speakers. This paper presented an acoustic depression detection classification using Linear and Quadratic Discriminant analysis with transition parameters and power spectral density as the acoustic features. Among the two features, power spectral density performed better, especially with the combination of band 1, 2 and 3 for both male and female data. As for the Transition parameters, we found that unvoiced feature performed best overall for both male and female.


Download File

[img]
Preview
PDF (Abstract)
Classifications of clinical depression detection using acoustic measures in Malay speakers.pdf

Download (34kB) | Preview

Additional Metadata

Item Type: Conference or Workshop Item (Paper)
Divisions: Faculty of Medicine and Health Science
DOI Number: https://doi.org/10.1109/IECBES.2016.7843521
Publisher: IEEE
Keywords: Clinical depression; Discrimant analysis; Power spectral density; Transition parameter
Depositing User: Nabilah Mustapa
Date Deposited: 03 Jul 2017 17:26
Last Modified: 03 Jul 2017 17:26
Altmetrics: http://www.altmetric.com/details.php?domain=psasir.upm.edu.my&doi=10.1109/IECBES.2016.7843521
URI: http://psasir.upm.edu.my/id/eprint/55964
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item