Auditory Content Analysis Based Digital Media Information Compression

Lots of repetition units exist in digital multimedia especially television programmes and other kinds of broadcastings. In this paper a new information compression algorithm named Auditory Content-Based Information Compression (ACBIC) is proposed to detect repeated programme segments in order to further reduce information redundancy. This algorithm is quite different from former data compression methods in that it realizes compression in semantic level through extracting auditory contents rather than signal statistic information. In our algorithm, Linear Predictive Coding (LPC) features are extracted at acoustic level, an LPC distance measure is defined to divide digital media stream into programme segments, and then auditory content description is created by statistically weighting LPC coefficients for each programme segment. Applying the idea of the dictionary table in LZW lossless data compression algorithm, a content-based information retrieval algorithm is developed to complete information comparation, selection, combination, and updating of the segmented programme units, similarly as data compression and decompression operations. Finally the experiments show an approving information compression result and confirm the completeness of the audio information redundance detection and the reversibility of the compression process. KeywordsAuditory Content-Based Information Compression; Dictionary Table; Information Redundancy; Auditory Content Description; LPC Distance Measure