期刊文献+

基于音频指纹技术的乐曲节拍识别系统 被引量:1

Music Beat Recognition System Based on Audio Fingerprint Technology
下载PDF
导出
摘要 针对当前乐曲节拍识别系统存在的一些缺陷,如精度低,误识率高等问题,为了获得更优的乐曲节拍识别结果,提出了基于音频指纹技术的乐曲节拍识别系统。首先分析当前乐曲节拍识别的研究进展,设计了乐曲节拍识别硬件系统的结构,然后对乐曲节拍信号进行采集和放大处理,建立乐曲节拍音频的指纹数据库,最后将待识别乐曲节拍指纹与数据库中的指纹进行匹配,根据匹配结果实现乐曲节拍识别。仿真实验结果表明,该系统提高了乐曲节拍识别精度,减少了乐曲节拍的漏识率,具有十分广泛的应用前景。 In view of some defects of the current music beat recognition system,such as low accuracy and high error rate,in order to obtain better music beat recognition results,a music beat recognition system based on audio fingerprint technology is proposed.Firstly,the research progress of music beat recognition is analyzed,and the structure of music beat recognition hardware system is designed.Then,the music beat signal is collected and amplified,and the fingerprint database of music beat audio is established.Finally,the fingerprint of music beat to be identified is matched with the fingerprint in the database,and the music beat recognition is realized according to the matching results,the accuracy of music beat recognition is high,and this system reduces the missing rate of music beat,and has a very wide application prospect.
作者 刘红梅 LIU Hongmei(College of Humanities and Arts,AKsu Vocational and Technical College,AKsu 843000,China)
出处 《微型电脑应用》 2021年第7期137-139,143,共4页 Microcomputer Applications
关键词 乐曲节拍 硬件系统 识别精度 漏识率 指纹数据库 tune beat hardware system recognition accuracy leakage rate fingerprint database
  • 相关文献

参考文献13

二级参考文献61

  • 1岳倩倩,周萍,景新幸.基于非线性幂函数的听觉特征提取算法研究[J].微电子学与计算机,2015,32(6):163-166. 被引量:5
  • 2刘维华,崔涛.基于内容的音频检索算法研究[J].计算机工程与设计,2006,27(16):3003-3006. 被引量:7
  • 3王让定,徐达文.基于提升小波的多重数字音频水印[J].电子与信息学报,2006,28(10):1820-1826. 被引量:16
  • 4王聪,刘国华,苑迎,张凌宇.一种基于子串运算的模式匹配方法[J].计算机工程与科学,2007,29(10):57-60. 被引量:2
  • 5Sert M, Baykal B, Yazici A. A robust and time-efficient fin- gerprinting model for musical audio consumer electronics [C]//International Symposium on Consumer Electronics, ISCE 2006. Petersburg: IEEE, 2006:1-6.
  • 6Deng Jijun, Wan Wanggen, Swaminathan Ram, et al. An audio fingerprinting system based on spectral energy structure C]//1ET International Conference on Smart and Sustainable City, ICSSC 2011. Shanghai: IEEE, 2011: 6-8.
  • 7Chen N, Xiao H D, Wan W G. Audio hash function based on non-negative matrix factorisation of mel-frequency cepstral coefficients [J]. lET Information Security, 2011, 5 (1) 19- 25.
  • 8Eric Allamanche, Jiirgen Herre, Oliver Hellmuth, et al. Content-based identification of audio material using mpeg-7 low level description[C]// International Symposium on Music Information Retrieval, ISMIR 2001. Bloomington: IEEE, 2001: 197-204.
  • 9Valero X, Alias F. Gammatone cepstral coefficients: Biologi- cally inspired features for non-speech audio classification mul- timedia[J]. IEEE Transactions on Multimedia, 2012, 14(6) : 1684-1689.
  • 10Huang Z, Yang X, Zhu X, et al. Homomorphic linear pre- dictive coding: A new estimation algorithm for all-pole speech modelling Communications[J]. Speech and Vision, 1990, 137 (2) : 103-108.

共引文献71

同被引文献2

引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部