Hierarchical System for Content

A hierarchical system for audio classiication and retrieval based on audio content analysis is presented in this paper. The system consists of three stages. The audio recordings are rst classiied and segmented into speech, music, several types of environmental sounds, and silence, based on morphological and statistical analysis of temporal curves of the energy function, the average zero-crossing rate, and the fundamental frequency of audio signals. The rst stage is called the coarse-level audio classiication and segmentation. Then, environmental sounds are classiied into ner classes such as applause, rain, birds' sound, etc., which is called the ne-level audio classiication. The second stage is based on time-frequency analysis of audio signals and the use of the hidden Markov model (HMM) for classiication. In the third stage, the query-by-example audio retrieval is implemented where similar sounds can be found according to the input sample audio. The way of modeling audio features with the hidden Markov model, the procedures of audio classiication and retrieval, and the experimental results are described. It is shown that, with the proposed new system, audio recordings can be automatically segmented and classiied into basic types in real time with an accuracy higher than 90%. Examples of audio ne classiication and audio retrieval with the proposed HMM-based method are also provided.