Abstract | ||
---|---|---|
Discovering peaks is a premise of audio fingerprinting algorithms for audio information retrieval, which focus on spectrogram peak pairs. In this paper, we discuss finding peaks in a two-direction scanning method which use a dynamic threshold vector to find local maximal point as peaks. And then an improved method using a slide window with two grids is proposed for discovering peaks at real-time. In this method, two key steps are executed alternately: scanning and sliding. In each scanning step, new peaks are found. When the slide window method is used, experiments on a database with 400,000 songs show that the average query time is shorten and the recall rate is slightly decreased. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1145/2499788.2499866 | ICIMCS |
Keywords | Field | DocType |
local maximal point,dynamic threshold vector,audio fingerprinting algorithm,key step,discovering peak,average query time,slide window,slide window method,improved method,audio information retrieval,real-time peak,fingerprint,real time | Pattern recognition,Recall rate,Spectrogram,Computer science,Speech recognition,Fingerprint,Artificial intelligence | Conference |
Citations | PageRank | References |
1 | 0.41 | 5 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tao Jiang | 1 | 15 | 3.31 |
Rihui Wu | 2 | 2 | 1.47 |
Jia-Hong Li | 3 | 28 | 2.59 |
Kang Xiang | 4 | 2 | 1.13 |
Feng Dai | 5 | 540 | 33.37 |