MULTI MODAL EMOTIONAL RECOGNITION SYSTEM USING FACIAL RECOGNITION AND SKEW GMM

Emotion recognition systems have a significant role in many areas including forensic application, teleconferencing, phone conversation and other areas. These emotions that are exhibited by the individuals can be sensitized through the facial expression and in remote conversations. These emotions can be figured out using the speech signals. These speech signals that are articulated from the voice can be generated and recorded. The recorded pattern using the features the emotions generated can be identified. Emotional recognition is a major research area in speech recognition. The features of the emotions will affect the recognition efficiency of the speech recognition systems. Several techniques are used in recognizing the emotions. This paper contributes towards a novel methodology based on Multi modal emotion recognition system using Skew Gaussian mixture model, the updated equations are derived from using EM Algorithm. The verbal communication signals are recorded into WAV format, which are used for research, collectively with the facial gestures. The emotions of both male and female are obtained using LPC, MFCC, and SDC.