A non-speech dataset built by a nine-classification discrete emotion model can be used for emotion recognition. The nine emotion dimensions are happy, angry, fearful, sad, brave, favorite, neutral, and calm. Recognition is performed by extracting their 384-dimensional feature vectors, which contain F0 envelopes, short-time excess zero rates, twelve-dimensional Meier cepstral coefficients, etc., as well as their first-order low-pass data. A total of 2,337 data samples were available.