• Nitin kumar
• Sharmelee Thangjam
• Harvinder Kaur

A number of methods have been developed in the field of human-computer interaction. The aim of this research is to observe and analyze the impact of emotions on the performance of individuals while performing their duties. In this article, the detection accuracy of the designed stress speech recognition system is measured for the students of collage during the exam time. To extract features, Mel Frequency Cepstral Coefficient is used along with grasshopper and Artificial Neural Network (ANN) as an optimization and classification technique respectively. The speech sample of students is collected manually and dataset of 30 students is formed. From the test results examined in MATLAB, the emotions are categorized into three types, high, medium and low. The detection accuracy of about 93.93 % is obtained.

Stress, Speech, MFCC, Grasshopper, ANN.

"ROBUST STRESS SPEECH RECOGNITION USING MFCC AND NEURAL NETWORK", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.7, Issue 10, page no.3554-3559, October-2020, Available :http://www.jetir.org/papers/JETIR2010463.pdf

"ROBUST STRESS SPEECH RECOGNITION USING MFCC AND NEURAL NETWORK", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.7, Issue 10, page no. pp3554-3559, October-2020, Available at : http://www.jetir.org/papers/JETIR2010463.pdf