Emotion Identification From Continuous Speech Using Cepstral Analysis

摘要

Emotion plays a major role in the area of psychology, human computer interaction, and robotics and BPO sectors. With the advancements in the field of communication technology, it is possible to establish the channel within few seconds across the globe. As most of the communication channels are public data transmission may not be authenticated. In such situation, before interacting, it is essential to recognize speaker by the unique features in the speech. A speaker can modulate his/her voice can changes his/her emotion state. Hence emotion recognition is required for the applications like telemetry, call centers, forensics and security. In our project the main emotion consider happy, angry, boredom, and sad. In this work we dealt with speaker recognition with different emotion. The basic emotions for this study include angry, sad, happy, boredom and neutral. The features we modeled using Gamma Distribution(GD) and data base generated with 50 speakers of both genders with the above basic emotions Considering feature vector combinations MFCC-LPC