Novel expressive speech classification algorithm based on multi-level extraction techniques

Presented paper deals with problems related to automatic recognition of expressive speech states. The analysis was performed using the Slovene part of the emotional speech corpus recorded under the international project Interface. The main focuses of presented emotional multi-level based feature extraction method are not the emotions itself but rather three expressive states: positive, negative and neutral. The main advantage of proposed method is the idea of multi-level feature extraction approach thus overcoming the problems related to time-frequency resolution compromise of signal analysis. For analysis, feature vectors of 210 elements were extracted for each analysis frame, with a window of analysis varying from 8–128ms.