Table 8.

Comparative analysis of the suggested SER system and the baseline SER system using the IEMOCAP and the EMO-DB speech corpus.

Authors/Reference/Year	Dataset	Un-Weighted Accuracy
Zhao et al. [37] (2019)	IEMOCAP	52.14%
Fayek et al. [54] (2017)	//	64.78%
Guo et al. [55] (2019)	//	57.10%
Zhang et al. [56] (2015)	//	40.02%
Han et al. [57] (2014)	//	51.24%
Meng et al. [53] (2019)	//	69.32%
Zhao et al. [58] (2019)	//	66.50%
Luo et al. [59] (2018)	//	63.98%
Jiang, S, et al. [60] (2019)	//	61.60%
Chen et al. [52] (2018)	//	64.74%
Issa et al. [61] (2020)	//	64.03%
Mustaqeem et al. [13] (2020)	//	72.25%
Proposed Method (2020)	//	77.01%
Guo et al. [55] (2019)	EMO-DB	84.49%
Meng et al. [53] (2019)	//	88.99%
Chen et al. [52] (2018)	//	82.82%
Badshah et al. [4] (2019)	//	80.79%
Jiang et al. [62] (2019)	//	84.53%
Issa et al. [61] (2020)	//	86.10%
Mustaqeem et al. [13] (2020)	//	85.57%
Proposed method (2020)	//	92.02%