TV Advertisements Detection and Clustering Based on Acoustic Information

Detection and clustering of commercial advertisements plays an important role in multimedia indexing as well as in the creation of personalized user content. Its aim is at detecting individual commercials within a broadcast and grouping together all repetitions of the same commercial over time. Several algorithms to tackle the detect task using either video and audio or only video cues have been found in existing literature, but none has been found for clustering.In this paper we present an acoustic-only system to perform both the detection and clustering of commercials. Detection is done in three steps, incrementally refining an initial coarse energy detection, while cluster is performed at a later stage over all previously detected commercials to find out how many times each commercial appears. Our detection system achieves 82% precision and recall using only acoustic information. For the clustering step, three algorithms are compared, obtaining best results using a modified dynamic Time Warping approach, which achieves 100% recall and 99% precision.