Voice Message Priorities Using Fuzzy Mood Identifier

Human language carries various kinds of information. In human telephone interaction, the detections of the emotional state of a speaker leaving a voice message on the answer machine as reflected in his or her utterances is crucial for determining the priority of the messages. This paper based on fuzzy inference system that can identify the mood of the person leaving a message on the answer machine and set apriori of the message. Several basic emotions from human speech including (very serious person (something important is happening like accident ...), regular person, person in a hurry, happy person and sad person). These emotions are classified into three categories according to priority of voice messages into urgent, normal and not urgent. Classification is carried out using speech analysis of different speakers to obtain the effective parameters, which represent the input of the fuzzy inference system