METHOD FOR EXTRACTING FEATURE VECTOR OF AUDIO DATA, COMPUTER READABLE MEDIUM STORING THE METHOD, AND METHOD FOR MATCHING THE AUDIO DATA USING THE METHOD

摘要

PURPOSE: A method for extracting a feature vector of audio data, a computer readable medium storing the method, and a method for matching audio data using the method are provided to convert sound sources of various formats into the same format and search a starting point of sound, thereby realizing fast extraction and accurate matching. CONSTITUTION: Audio data is inputted. The audio data is decoded(S12). A starting point of sound is searched in the decoded data(S15). A feature vector is extracted by processing data after the searched starting point(S17). The audio data is partial data corresponding to a section from a reproduction time point of the audio data to a fixed reproduction time point.