Generic content-based audio indexing and retrieval framework

摘要

Rapid increase in the amount of the digital audio collections presenting various formats, types, durations and other parameters that the digital multimedia world refers demands a generic framework for robust and efficient indexing and retrieval based on the aural content. Moreover, from the content-based multimedia retrieval point of view, the audio information can be even more important than the visual part as it is mostly unique and significantly stable within the entire duration of the content. A generic and robust audio-based multimedia indexing and retrieval framework, which has been developed and tested under the MUVIS system, is presented. This framework supports the dynamic integration of the audio feature extraction modules during the indexing and retrieval phases and therefore provides a test-bed platform for developing robust and efficient aural feature extraction techniques. Furthermore, the proposed framework is designed based on the high-level content classification and segmentation in order to improve the speed and accuracy of the aural retrievals. Both theoretical and experimental results are finally presented, including the comparative measures of retrieval performance with respect to the visual counterpart.