Fast parallel algorithm for audio content retrieval on GPUs

Author

Sanabria, Adriana ; Oyaga, Jaime Vitola ; Bonilla, César Pedraza

Author_Institution

Electron. Eng. Dept., Santo Tomas Univ., Bogota, Colombia

fYear

2011

fDate

4-6 May 2011

Firstpage

1

Lastpage

4

Abstract

The search techniques audio content MIR (music information retrieval) face two major challenges: the robustness of the algorithm and the speed of this operation. In this article proposes a model of fast algorithm for the extraction of audio data by the fingerprinting technique, which is implemented on a CPU-based platform and then parallelized to run on a graphics hardware (GPU). Tests on GPU determined a success rate close to 100% and response times approximately 2 times lower than those obtained with a PC workstation, allowing searches of up to 65 commercial in real-time.

Keywords

audio signal processing; computer graphic equipment; content-based retrieval; coprocessors; music; CPU-based platform; GPU; audio content retrieval; fast parallel algorithm; fingerprinting technique; graphics hardware; music information retrieval; search techniques audio content MIR; Algorithm design and analysis; Correlation; Databases; Graphics processing unit; Real time systems; Robustness; Software algorithms;

fLanguage

English

Publisher

ieee

Conference_Titel

Computing Congress (CCC), 2011 6th Colombian

Conference_Location

Manizales

Print_ISBN

978-1-4577-0285-3

Type

conf

DOI

10.1109/COLOMCC.2011.5936339

Filename

5936339