Mohammed Ahmed, Swaleha Shaikh, Hera Ansari and Arshi Siddiqui M.H.Saboo Siddik College Of Engineering, India
ABSTRACT
Audio or music fingerprints can be utilize to implement an economical music identification system on amillion-song library, however the system needs great deal of memory to carry the fingerprints and indexes.Therefore, for a large-scale audio library, memory imposes a restriction on the speed of musicidentifications. So, we propose an efficient music identification system which used a kind of space-savingaudio fingerprints. For saving space, original finger representations are sub-sample and only one quartersof the original data is reserved. In this approach, memory demand is far reduced and therefore the searchspeed is criticalincreasing whereas the lustiness and dependability ar well preserved. Mappingaudio information to time and frequency domain for the classification, retrieval or identification tasks presents four principal challenges. The dimension of the input should be considerably reduced;the ensuing options should be strong to possible distortions of the input; the feature should be informativefor the task at hand simple. We propose distortion free system which fulfils all four of these requirements.Extensive study has been done to compare our system with the already existing ones, and the results showthat our system requires less memory, provides fast results and achieves comparable accuracy for a largescale database.
KEYWORDS Audio Fingerprint, Fingerprint Extraction, Audio Template, Fast Fourier transform, Database Search Original Source URL: http://aircconline.com/acii/V3N2/3216acii03.pdf http://airccse.org/journal/acii/vol3.html
No comments:
Post a Comment