抄録
Human interaction with social networking services (SNS) is currently a very active research area. SNS posts, such as tweets, allow users to broadcast their ideas in short form of text, voice, or images, using mobile devices and computers. Text and speech enriched with emotions is one of the major ways of exchanging ideas, especially via telephony and SNS. By analyzing a voice stream using a Hidden Markov Model (HMM) and Log Frequency Cepstral Coefficients (LFPC) based system, different emotions can be recognized. Using a simple Java client, recognized emotions can be delivered to a server as an index. A mobile client can then retrieve the emotion and display it through colored icons. Each emotion is mapped to a particular color, as it is natural to use colors to represent various expressions. Not only colors, we also use avatar animation models in different environments for the expression of different emotions.
