Analysis of Prosodic Feature Vectors from Speeches of Severity-based Major Depression Disorder Patients in Nigeria

Authors

  • Stephen Gbenga Akinbode
  • Iyinoluwa Tioluwani Idowu
  • Olayinka Olufunmilayo Olusanya
  • Temilade Aderounmu
  • Peter Adebayo Idowu Obafemi Awolowo University Nigeria

DOI:

https://doi.org/10.33003/fjs-2026-1016-5865

Keywords:

Major depressive disorder, speech prosody, acoustic features, exploratory data analysis, feature fusion

Abstract

Diabetes mellitus remains a major metabolic disorder requiring safer and affordable therapeutic alternatives. This study evaluated the safety profile, in vitro antidiabetic activity, and phytochemical composition of a formulated polyherbal syrup (PHS) prepared from Vernonia amygdalina, Moringa oleifera, Zingiber officinale, Allium cepa, and Allium sativum. Aqueous extracts of onion, garlic, and ginger were obtained by decoction of 20 g powdered samples in 100 mL distilled water at 40 °C for 3 h, while fresh leaves of Moringa oleifera and Vernonia amygdalina were extracted by manual juice expression and filtration. The extracts were combined with honey to produce the polyherbal syrup. Acute toxicity evaluation in albino rats using oral doses of 1000–16000 mg/kg body weight revealed no mortality or visible signs of toxicity, indicating an LD₅₀ greater than 16000 mg/kg. Sub-acute toxicity studies conducted at doses of 25–400 mg/kg also showed no adverse behavioral or physiological changes. In vitro antidiabetic assays revealed that PHS is concentration-dependent. The PHS exhibited IC₅₀ values (µg/mL) of 8.88 for glucose uptake, 2.55 for α-amylase inhibition, and 3.50 for α-glucosidase inhibition, compared with the standard drug acarbose, which showed IC₅₀ values of 3.55, 1.89, and 3.39 µg/mL, respectively. Although the standard drug showed slightly higher potency, the PHS demonstrated comparable α-glucosidase inhibitory activity. GC–MS profiling revealed numerous bioactive phytochemicals including 2,3-dihydro-3,5-dihydroxy-6-methyl-4H-pyran-4-one,

References

Otte, C., Gold, S. M., Penninx, B. W., Pariante, C. M., Etkin, A., Fava, M., ... & Schatzberg, A. F. (2016). Major depressive disorder. Nature reviews Disease primers, 2(1), 16065.

Patel, S. (2025, October 20). How Many People Live with Depression? Advance Study. Retrieved April 12, 2026, from https://advancestudy.org/how-many-people-live-with-depression/

Ugoeze, N. O. (2025). World Mental Health Day: 85% unreached as Nigeria buckles under massive care gap. The Guardian. https://guardian.ng/featured/world-mental-health-day-85-unreached-as-nigeria-buckles-under-massive-care-gap/#:~:text=Obindo%20informed%20that%20about%2085,treatment%20and%20inadequate%20medical%20facilities.

Lin, L., Chen, X., Shen, Y., & Zhang, L. (2020). Towards Automatic Depression Detection: A BiLSTM/1D CNN-Based Model. Applied Science, 10(23), 1-20

Cummins, N., Scherer, S., Krajewski, J., Schnieder, S., Epps, J., & Quatieri, T. F. (2015). A review of depression and suicide risk assessment using speech analysis. Speech communication, 71, 10-49.

Seifpanahi, M. S., Ghaemi, T., Ghaleiha, A., Sobhani-Rad, D., & Zarabian, M. K. (2023). The association between depression severity, prosody, and voice acoustic features in women with depression. The Scientific World Journal, 2023(1), 9928446.

Yang, Y., Fairbairn, C., & Cohn, J. F. (2012). Detecting depression severity from vocal prosody. IEEE transactions on affective computing, 4(2), 142-150

Mengesha, Z., Heldreth, C., Lahav, M., Sublewski, Juliana., and Tuennerman, E. (2021). “I don’t Think These Devices are Very Culturally Sensitive.” Impact of Automated Speech Recognition Errors on African Americans Frontiers in Artificial Intelligence Volume 4 https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2021.725911/ https://doi.org/10.3389/frai.2021.725911 ISSN2624-8212

Mundt, J. C., Snyder, P. J., Cannizzaro, M. S., Chappie, K., & Geralts, D. S. (2007). Voice acoustic measures of depression severity and treatment response collected via interactive voice response (IVR) technology. Journal of neurolinguistics, 20(1), 50-64.

Wadle, L. M., Ebner-Priemer, U. W., Foo, J. C., Yamamoto, Y., Streit, F., Witt, S. H., ... & Sirignano, L. (2024). Speech features as predictors of momentary depression severity in patients with depressive disorder undergoing sleep deprivation therapy: ambulatory assessment pilot study. JMIR mental health, 11, e49222.

Gillespie, S., Moore, E., Laures-Gore, J., & Farina, M. (2016, March). Exploratory analysis of speech features related to depression in adults with Aphasia. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 5815-5819). IEEE.

Extracted Acoustic and Prosodic Feature Elements of Participants

Downloads

Published

08-09-2026

How to Cite

Akinbode, S. G., Idowu, I. T., Olusanya, O. O., Aderounmu, T., & Idowu, P. A. (2026). Analysis of Prosodic Feature Vectors from Speeches of Severity-based Major Depression Disorder Patients in Nigeria. FUDMA Journal of Sciences, 10(16), 589-593. https://doi.org/10.33003/fjs-2026-1016-5865

Most read articles by the same author(s)