Hybrid CNN-Transformer reaches 97.8% accuracy and 0.98 macro F1 on the EYASE Egyptian Arabic speech emotion dataset.
OpenSMILE – The Munich versatile and fast open-source audio feature extractor
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Hybrid CNN-Transformer Architecture for Arabic Speech Emotion Recognition
Hybrid CNN-Transformer reaches 97.8% accuracy and 0.98 macro F1 on the EYASE Egyptian Arabic speech emotion dataset.