Research of a Semantics-Based Music Information Aggregation and Retrieval System for P2P Network
Qiong Wu · Microcomputer applications · 2008
As the digital music collections in Peer-to-Peer(P2P)network expand larger and larger,music information retrieval(MIR)is becoming a crucial problem in the P2P music-sharing systems.We propose a semantics-based music information aggregation and retrieval system especially for P2P network.First,an extendable music ontology is defined;then we bring the proposal of aggregating the multi-information which contain auto-extracted features,user-annotated descriptors and Web metadata,etc.,and introduce the related extractor-aggregator tool developed based on CLAM Annotator module;furthermore,a method based on the RDFPeers framework is introduced to reposit and query both the static and the dynamic information.The proposed system extends the MIR in P2P network from the traditional title/name keyword retrieval to semantics-based information retrieval.The evaluation of the demonstration model also shows that the proposed multi-information aggregation mentod optimizes the retrieval accuracy and recall.