Hierarchical classification of audio data for archiving and retrieving

A hierarchical system for audio classi cation and retrieval based on audio content analysis is presented in this paper. The system consists of three stages. The rst stage is called the coarse-level audio classi cation and segmentation, where audio recordings are classi ed and segmented into speech, music, several types of environmental sounds, and silence, based on morphological and statistical analysis of temporal curves of short-time features of audio signals. In the second stage, environmental sounds are further classi ed into ner classes such as applause, rain, birds' sound, etc. This ne-level classi cation is based on timefrequency analysis of audio signals and use of the hidden Markov model (HMM) for classi cation. In the third stage, the query-by-example audio retrieval is implemented where similar sounds can be found according to an input sample audio. It is shown that the proposed system has achieved an accuracy higher than 90% for coarse-level audio classi cation. Examples of audio ne classi cation and audio retrieval are also provided.