Speech Emotion Recognition: A Multi-Dataset Experimental Study

Main Article Content

Suhad Al-Shoukry
Rihab Habeeb Sahib
Wurood Mahdi Sahib
Abdulkadhem A. Abdulkadhem
Mohamed Shabbir Abdulnabi

Abstract

Speech emotion recognition involves identifying emotions from speech recordings. When some emotions are more frequent than others in a dataset, overall accuracy can mask two kinds of errors: missing an emotion when it is present and predicting it when it is absent. In this study, we evaluated the Enhanced Speech Emotion Recognition Framework (ESERF) on eight emotion categories using recordings from RAVDESS, CREMA-D, and TESS. We assessed performance across three experimental scenarios using overall accuracy, confusion matrices, and class-wise precision, recall, and F1-score. Overall accuracy was 60.74%, 61.02%, and 49.22% in Scenarios 1, 2, and 3, respectively. Although the first two scenarios had similar overall accuracy, recall for Calm increased from 0.80 to 0.87, while precision fell from 0.64 to 0.44. Scenario 2 therefore identified a larger proportion of the Calm recordings, but fewer than half of the recordings it classified as Calm carried that label. The decline in recall from Scenario 2 to Scenario 3 also varied by emotion: recall fell by about 25 percentage points for both Fear and Happy, compared with only two percentage points for Sad.

Article Details

Section

Articles

How to Cite

[1]
Suhad Al-Shoukry, Rihab Habeeb Sahib, Wurood Mahdi Sahib, Abdulkadhem A. Abdulkadhem, and Mohamed Shabbir Abdulnabi, “Speech Emotion Recognition: A Multi-Dataset Experimental Study”, Babylonian Journal of Machine Learning, vol. 2026, pp. 333–350, Nov. 2026, doi: 10.58496/BJML/2026/019.