Abstract | ||
---|---|---|
Computations in most music retrieval systems strongly depend on the size of data compared. We propose to enhance performances of a music retrieval system, namely a harmonic similarity evaluation method, by first indexing relevant parts of music pieces. The indexing algorithm represents each audio piece exclusively by its major repetition, using harmonic descriptions and string matching techniques. Evaluations are performed in the context of a state-of-the-art retrieval method, namely cover songs identification, and results highlight the success of our indexing system in keeping similar results while yielding a substantial gain in computation time. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1145/2009916.2010102 | SIGIR |
Keywords | Field | DocType |
indexing system,state-of-the-art retrieval method,indexing method,computation time,harmonic similarity evaluation method,music piece,audio piece,indexing algorithm,music retrieval system,indexing relevant part,harmonic description,indexation,string matching | String searching algorithm,Music information retrieval,Information retrieval,Computer science,Harmonic,Search engine indexing,Speech recognition,Computation,Speedup | Conference |
Citations | PageRank | References |
0 | 0.34 | 4 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Benjamin Martin | 1 | 3 | 0.82 |
Pierre Hanna | 2 | 110 | 20.53 |
Matthias Robine | 3 | 74 | 13.06 |
Pascal Ferraro | 4 | 77 | 11.54 |