• Kris Negi
• Ishika Sindhi
• Komal Garg
• Khushi Gambhir

Human emotion recognition through machine intelligence has been a topic of interest from many years. Mechanisms such as speech processing, pattern recognition and machine learning has made it possible for a machine to understand the emotional state of a person with accuracy and simplicity. Features of speech such as pitch, wavelet, Mel Frequency cepstrum coefficients (MFCC) are used by these machines to classify the human emotions into several classes such as sad, anger, happy, neutral, etc. This paper features a survey of the various researches carried out on the speech emotion recognition (SER) domain. A brief explanation to the various stages of SER, classifiers such as K-Nearest Neighbour (K-NN) and Gaussian Mixture Model (GMM) and the performance analysis, using parameters such as F-measure, precision, recognition rate, etc. has been provided in this survey.

Speech recognition system, Machine learning, Gaussian mixture model, KNN, MFCC, Pitch.

"Speech Recognition: A Review on Its Methodological Aspects", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 4, page no.646-649, April-2019, Available :http://www.jetir.org/papers/JETIR1904J85.pdf

"Speech Recognition: A Review on Its Methodological Aspects", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 4, page no. pp646-649, April-2019, Available at : http://www.jetir.org/papers/JETIR1904J85.pdf