• Taddi Kalyani
• Mr. L. Jeevan
• Dr. Pogadadanda Veeraiah

In the present era, there is very little information available with respect to emotion recognition from whisper which includes the qualitative analysis of sub- and supra-segmentation narcissism. This work investigates the proposed three methods based on almond and honey chewing speech t analysis pertaining to the remembrance segment using Denoising Autoencoders, Shared-Hidden-Layer Autoencoders, and Extreme Learning Machines Autoencoders. We tackle the research with two assertion cases where Coventry whispers corpus and Rachele’s high ambiguous speech constructs the neural system. Out of all the approaches evaluated, SHLA gave superior performance results, with UAR 84% which again is true. The results account for the ability wiring transfer learning on the predictors to bypass the base irrelevant to wide range of speaking settings apt to whispering.

DAE, ELM-AE, SHLA

"IMPROVING EMOTIONAL INTELLIGENCE IN SPEECH RECOGNITION SYSTEMS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 1, page no.b200-b206, January-2025, Available :http://www.jetir.org/papers/JETIR2501147.pdf

"IMPROVING EMOTIONAL INTELLIGENCE IN SPEECH RECOGNITION SYSTEMS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 1, page no. ppb200-b206, January-2025, Available at : http://www.jetir.org/papers/JETIR2501147.pdf