收稿日期: 2016-11-16
修回日期: 2017-03-20
网络出版日期: 2017-11-30
基金资助
国家自然科学基金面上项目（No.61571282）资
Music Comparison Algorithm Based on Intelligent Wearable Device
Received date: 2016-11-16
Revised date: 2017-03-20
Online published: 2017-11-30
叶旸, 张雪凡, 刘源, 王臣, 黄庆 . 基于智能可穿戴设备的乐音对比算法[J]. 应用科学学报, 2017 , 35(6) : 706 -716 . DOI: 10.3969/j.issn.0255-8297.2017.06.004
We introduce a novel algorithm for music comparison based on intelligent wearable devices. The algorithm includes three steps. First, the note initial point is identified with an average amplitude method, and frequency information obtained with short time Fourier transform according to the characteristics of music. Second, the basic frequency is extracted with subharmonic summation and minimum variance methods to locate music note accurately. Third, the real-time music and standard music are compared both in the frequency and time domains to detect errors in terms of Euclidean distance. Experiments show that the algorithm has low computational complexity, good real-time performance and high accuracy. It is suitable for music comparison based on intelligent wearable device.
[1] Sazaki Y, Ayuni R, Kom S. Musical note recognition using minimum spanning tree algorithm[C]//International Conference on Telecommunication Systems Services and Applications. IEEE, 2014:1-5.
[2] 谢俊祥,张琳. 智能可穿戴设备及其应用[J]. 中国医疗器械信息,2015(3):18-23. Xie J X, Zhang L. The review and applications of smart and wearable devices[J]. China Medical Device Information, 2015(3):18-23. (in Chinese)
[3] 徐国庆,杨丹,王彬洁,文俊浩. 乐音识别方法及应用[J]. 计算机应用,2005, 25(4):968-970. Xu G Q, Yang D, Wang B J, Wen J H. Method and the application of musical tone recognition[J]. Journal of Computer Applications, 2005, 25(4):968-970. (in Chinese)
[4] Wu D,Yin Y,Jiang H. Large-margin estimation of hidden Markov models with second-order cone programming for speech recognition[J]. IEEE Transactions on Audio Speech & Language Processing, 2011, 19(6):1652-1664.
[5] 李超,熊璋,薛玲,刘云. 一种阈值自适应调整的实时音频分割方法[J]. 北京航空航天大学学报,2005, 31(12):1317-1321. Li C, Xiong Z, Xue L, Liu Y. Adaptive threshold method for real-time audio segmentation[J]. Journal of Beijing University of Aeronautics and Astronautics, 2005, 31(12):1317-1321. (in Chinese)
[6] 张鹏远,计哲,侯炜,金鑫,韩卫生. 一种小资源下语音识别算法设计与优化[C]//全国人机语音通讯学术会议,2015:343-348.
[7] Akbari M, Targhi A T, Dehshibi M M. TeMu-app:music characters recognition using HOG and SVM[C]//Machine Vision and Image Processing, 2015.
[8] Wu D, Zhao H, Huang C, Huang C W, Xiao Z Z, Zhang X J, Xu Y S, Tao Z. Speech endpoint detection in low-SNRs environment based on perception spectrogram structure boundary parameter[J]. Chinese Journal of Acoustics, 2014, 39(4):392-399.
[9] Jalil M, Butt F A, Malik A. Short-time energy, magnitude, zero crossing rate and autocorrelation measurement for discriminating voiced and unvoiced segments of speech signals[C]//International Conference on Technological Advances in Electrical, Electronics and Computer Engineering. IEEE, 2013:208-212.
[10] 刘伟. 音乐音符识别的方法[D]. 吉林:吉林大学,2008.
[11] 宋知用. MATLAB在语音信号分析与合成中的应用[M]. 北京:北京航空航天大学出版社,2013:22-25.
[12] 杨静,郑恩让,张玲,马令坤. 基于FPGA的FFT处理器设计与实现[J]. 化工自动化及仪表,2010, 37(3):107-109. Yang J, Zheng E R, Zhang L, Ma L K. Design and implementation of FFT processor based on FPGA[J]. Control and Instruments in Chemical Industry, 2010, 37(3):107-109. (in Chinese)
[13] Hermes D J. Measurement of pitch by subharmonic summation[J]. Journal of the Acoustical Society of America, 1988, 83(1):257-264.
[14] 刘淑华,胡强,覃团发,梁琳. 基于自相关函数最大值的语音端点检测方法[J]. 电声技术,2006(12):47-50. Liu S H, Hu Q, Qin T F, Liang L. A method of the voice endpoint detection based on maximum of autocorrelation function[J]. Voice technology, 2006(12):47-50. (in Chinese)
[15] Ananthashayana V K. Fourier-analysis and signal-processing by use of the mobius inversion formula-comment[J]. IEEE Transactions on Signal Processing, 1992(3):676.
[16] 曹宁,虞湘滨. 基于FFT的快速小波变换算法研究[J]. 河海大学常州分校学报, 2001, 15(3):1-5. Cao N, Yu X B. The algorithm research of fast wavelet transform based on FFT[J]. Journal of Hohai University Changzhou, 2001, 15(3):1-5. (in Chinese)
/
| 〈 |
|
〉 |
