%0 Conference Proceedings
%T An Effective Approach for Vocal Melody Extraction from Polyphonic Music on GPU
%+ State key Laboratory of Software Development Environment [Beijing]
%+ School of Computer Science and Engineering [Beijing]
%+ School of Computer Engineering and Science [Shanghai]
%A Yao, Guangchao
%A Zheng, Yao
%A Xiao, Limin
%A Ruan, Li
%A Lin, Zhen
%A Peng, Junjie
%Z Part 4: Session 4: Multi-core Computing and GPU
%< avec comité de lecture
%( Lecture Notes in Computer Science
%B 10th International Conference on Network and Parallel Computing (NPC)
%C Guiyang, China
%Y Ching-Hsien Hsu
%Y Xiaoming Li
%Y Xuanhua Shi
%Y Ran Zheng
%I Springer
%3 Network and Parallel Computing
%V LNCS-8147
%P 284-297
%8 2013-09-19
%D 2013
%R 10.1007/978-3-642-40820-5_24
%Z Computer Science [cs]Conference papers
%X Melody extraction from polyphonic music is a valuable but difficult problem in music information retrieval. The extraction incurs a large computational cost that limits its application. Growing processing cores and increased bandwidth have made GPU an ideal candidate for the development of fine-grained parallel algorithms. In this paper, we present a parallel approach for salience-based melody extraction from polyphonic music using CUDA. For 21 seconds of polyphonic clip, the extraction time is cut from 3 seconds to 33 milliseconds using NVIDIA GeForce GTX 480 which is up to 100 times faster. The increased performance allows the melody extraction to be carried out for real-time applications. Furthermore, the evaluation of the extraction on huge datasets is also possible. We give insight into how such significant speed gains are made and encourage the development and adoption of GPU in music information retrieval field.
%G English
%2 https://inria.hal.science/hal-01513779/document
%2 https://inria.hal.science/hal-01513779/file/978-3-642-40820-5_24_Chapter.pdf
%L hal-01513779
%U https://inria.hal.science/hal-01513779
%~ IFIP-LNCS
%~ IFIP
%~ IFIP-NPC
%~ IFIP-LNCS-8147