Note Onset Detection Based on Constant Q Transform

doi:10.3969/j.issn.1000-3428.2013.10.061

Computer Engineering

Previous Articles Next Articles

Note Onset Detection Based on Constant Q Transform

GUI Wen-ming ^1,2, LIU Rui-fan ¹, SHAO Xi ³, BAI Guang-yi^1,4

(1. School of Computer Science and Technology, Nanjing University of Science and Technology, Nanjing 210094, China; 2. Nanjing University of Finance and Economics, Nanjing 210046, China; 3. Nanjing University of Posts and Telecommunications, Nanjing 210003, China; 4. Noah Solution(Suzhou) Co., Ltd., Suzhou 215021, China)

Received:2012-08-23 Online:2013-10-15 Published:2013-10-14

基于常量Q变换的音符起始点检测

桂文明^1,2，刘睿凡¹，邵曦³，白光一^1,4

(1. 南京理工大学计算机科学与技术学院，南京 210094；2. 南京财经大学，南京 210046； 3. 南京邮电大学，南京 210003；4. 方舟信息技术(苏州)有限公司，江苏苏州 215021)

作者简介:桂文明(1974－)，男，博士研究生，主研方向：音乐信号处理；刘睿凡，博士研究生；邵曦，副教授、博士；白光一，研究员、博士生导师
基金资助:
国家自然科学基金资助项目“基于内容的流行音乐结构分析的研究”(60902065)

Abstract

Abstract: The frequencies of music scales are exponentially distributed. This paper proposes an algorithm for note onset detection, which is based on Constant Q Transform(CQT) and adapts to the characteristics of music scales. The music signals are decomposed to a partial matrix through CQT, according to the frequencies distribution of twelve-tone equal temperament. Detection function is generated using the partial matrix. Peaks are picked, and note onset vector is obtained. Experimental results show that the results are superior to those of 2011 MIREX.

Key words: note onset detection, twelve-tone equal temperament, Constant Q Transform(CQT), Short Time Fourier Transform(STFT), partial matrix, peak picking

摘要： 针对音乐的音阶频率按指数规律分布的特点，提出基于常量Q变换(CQT)的音符起始点检测算法。该算法根据十二平均律的音阶频率分布规律，对音乐信号进行分解，得到一个分音矩阵，利用该分音矩阵生成检测函数，并提取峰值，得到音符起始点向量。实验结果显示，该算法的检测结果要优于2011年MIREX的结果。

关键词: 音符起始点检测, 十二平均律, 常量Q变换, 短时傅里叶变换, 分音矩阵, 峰值提取

CLC Number:

TP391

GUI Wen-ming, LIU Rui-fan, SHAO Xi, BAI Guang-yi. Note Onset Detection Based on Constant Q Transform[J]. Computer Engineering, doi: 10.3969/j.issn.1000-3428.2013.10.061.

桂文明，刘睿凡，邵曦，白光一. 基于常量Q变换的音符起始点检测[J]. 计算机工程, doi: 10.3969/j.issn.1000-3428.2013.10.061.

/ / Recommend / Download Citations

URL: http://www.ecice06.com/EN/10.3969/j.issn.1000-3428.2013.10.061

http://www.ecice06.com/EN/Y2013/V39/I10/283

References

参考文献 [1] Casey M A, Veltkamp R, Goto M, et al. Content-based Music Information Retrieval: Current Directions and Future Challenges[J]. Proceedings of the IEEE, 2008, 96(4): 668-696. [2] Shao Xi. Contend-based Music Classification Summarization and Retrieval[D]. Singapore: National University of Singapore, 2006. [3] Goto M. An Audio-based Real-time Beat Tracking System for Music with or Without Drum-sounds[J]. Journal of New Music Research, 2001, 30(2): 159-171. [4] 陈哲, 许洁萍. 基于内容的音乐节拍跟踪[J]. 电子学报, 2009, 37(S1): 156-160. [5] Bello J P, Daudet L, Abdallah S, et al. A Tutorial on Onset Detection in Music Signals[J]. IEEE Transactions on Speech and Audio Processing, 2005, 13(5): 1035-1047. [6] Duxbury C M S, Davies M. A Hybrid Approach to Musical Note Onset Detection[C]//Proc. of Digital Audio Effects Conference. Hamburg, Germany: [s. n.], 2002. [7] Holzapfel A, Stylianou Y, Gedik A C, et al. Three Dimensions of Pitched Instrument Onset Detection[J]. IEEE Transactions on Audio, Speech, and Language Processing, 2010, 18(6): 1517-1527. [8] Tan Huili, Zhu Yongwei, Chaisorn L, et al. Audio Onset Detection Using Energy-based and Pitch-based Processing[C]// Proc. of International Symposium on Circuits and Systems. [S. l.]: IEEE Press, 2010: 3689-3692. [9] 桂文明, 邵曦, 刘睿凡. 一种新型音符起始点检测算法[J]. 计算机工程与应用, 2011, 47(24): 9-11. [10] Daudet L. Transients Modeling by Pruned Wavelet Trees[C]// Proc. of International Computer Music Conference. Havana, Cuba: [s. n.], 2001: 18-21. [11] 周复三. 音乐基础理论教程[M]. 济南: 山东大学出版社, 2005. [12] Brown J C. Calculation of a Constant Q Spectral Transform[J]. Journal of the Acoustical Society of America, 1991, 89(1): 425-434. [13] Pertusa A. Computationally Efficient Methods for Polyphonic Music Transcription[D]. Alicante, Spain: Repositorio Institucional de la Universidad de Alicante, 2010. 编辑顾逸斐

Please choose a citation manager

Content to export

Note Onset Detection Based on Constant Q Transform

基于常量Q变换的音符起始点检测

PDF

Knowledge

Cited

Abstract

Cite this article

share this article

References

Related Articles 3

Recommended Articles

Metrics

Comments

[1]	TANG Yonghe,JIANG Liehui,HOU Yifan,WANG Ruimin. Contactless Fingerprint Image Enhancement Based on Retinex and STFT [J]. Computer Engineering, 2017, 43(2): 248-251,256.
[2]	NAI Chang-Shen, JIN Chao-Di, LIU Yu-Jiang, LIU Jing-Cai, DONG Lu. Stratum Identification of Drilling Based on Complex Morlet Wavelet [J]. Computer Engineering, 2012, 38(7): 13-15.
[3]	GUAN Xin, LI Qiang, TIAN Hong-Wei. Note Onset Automatic Detection Based on Differential All Phase MFCC [J]. Computer Engineering, 2010, 36(11): 25-26,29.

模态框（Modal）标题

Please choose a citation manager

Content to export

Note Onset Detection Based on Constant Q Transform

基于常量Q变换的音符起始点检测

PDF

Knowledge

Cited

Abstract

Cite this article

share this article

References

Related Articles 3

Recommended Articles

Metrics

Comments