The traditional expert-based instrumental music evaluation strategy can’t meet the requirements of the rapidly accumulated audio data. The traditional strategy not only takes a high cost of human’s energy and time but also may have some problems on consistency and fairness of judgment. This paper aims at designing a complete recognition and evaluation strategy to automatically identify the timber of wind instruments. We take the clarinet as example and propose a strategy based on multi-feature fusion and random forest. First, we use the identification of fundamental frequency algorithm to automatically distinguish the notes performed by the instruments. Second, we extract 3 types of features including MFCC, brightness and roughness to describe the instrumental signals. Then, considering two kinds of variants: note and tone quality, we design 5 strategies to remove the influence of different notes in the evaluation of tone quality. By analyzing these strategies, we explore the optimal strategy for the recognition. The final evaluation results over 840 music slices demonstrate the effectiveness of this method.
| Published in | American Journal of Networks and Communications (Volume 5, Issue 2) |
| DOI | 10.11648/j.ajnc.20160502.11 |
| Page(s) | 11-16 |
| Creative Commons |
This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited. |
| Copyright |
Copyright © The Author(s), 2024. Published by Science Publishing Group |
Tone Quality, Timbre Analysis, Audio Signal Processing, Random Forest
| [1] | Yu-Hsiang H, Chao-Ton S. Multiclass MTS for saxophone timbre quality inspection using waveform-shape-based features [J]. IEEE Transactions on Systems Man & Cybernetics Part B Cybernetics A Publication of the IEEE Systems Man & Cybernetics Society, 2009, 39(3): 690-704. |
| [2] | Paulus J, Klapuri A. Music Structure Analysis Using a Probabilistic Fitness Measure and an Integrated Musicological Model. [C] ISMIR 2008, 9th International Conference on Music Information Retrieval, Drexel University, Philadelphia, PA, USA, September 14-18, 2008. 2008: 369-374. |
| [3] | Typke R, Veltkamp R C, Wiering F. Searching notated polyphonic music using transportation distances [C]. Acm Multimedia Conference. 2004: 128-135. |
| [4] | Downie S, Nelson M. Evaluation of a Simple and Effective Music Information Retrieval Method [C] Research & Development in Information Retrieval. SIGIR '00 Proceedings of the 23rd annual international ACM SIGIR conference on Research and developm, 2000: 73-80. |
| [5] | K. Roger B. Dannenberg, Ning Hu. Pattern Discovery Techniques for Music Audio [J]. Journal of New Music Research, 2003, 32(2): 63-70. |
| [6] | Yu Y, Zimmermann R, Wang Y, et al. Recognition and Summarization of Chord Progressions and Their Application to Music Information Retrieval[C]. Multimedia (ISM), 2012 IEEE International Symposium on. 2012: 9-16. |
| [7] | Guo J, Ding M, Guan X, et al. Timbre identification of instrumental music via energy distribution modeling[C]. Proceedings of the 7th International Conference on Internet Multimedia Computing and Service. ACM, 2015: 1-5. |
| [8] | Cheveigné A D, Kawahara H. YIN, a fundamental frequency estimator for speech and music [J]. Journal of the Acoustical Society of America, 2002, 111(4): 1917-30. |
| [9] | Valero X, Alias F. Gammatone Cepstral Coefficients: Biologically Inspired Features for Non-Speech Audio Classification [J]. IEEE Transactions on Multimedia, 2012, 14(6): 1684-1689. |
| [10] | Logan B. Mel Frequency Cepstral Coefficients for Music Modeling [C]. In International Symposium on Music Information Retrieval. 2000. |
| [11] | Sethares W A. Tuning, Timbre, Spectrum, Scale [M]. Springer London, 2005. |
| [12] | Vassilakis P N. Perceptual and Physical Properties of Amplitude Fluctuation and their Musical Significance [J]. Acta ibérica radiológica-cancerológica, 2001, 28(4): 119-128. |
| [13] | Biau G. Analysis of a Random Forests Model [J]. Journal of Machine Learning Research, 2010, 13(2): 1063-1095. |
APA Style
Zhe Lei, Mengying Ding, Xiaohong Guan, Youtian Du, Jicheng Feng, et al. (2016). Tone Quality Recognition of Instruments Based on Multi-feature Fusion of Music Signal. American Journal of Networks and Communications, 5(2), 11-16. https://doi.org/10.11648/j.ajnc.20160502.11
ACS Style
Zhe Lei; Mengying Ding; Xiaohong Guan; Youtian Du; Jicheng Feng, et al. Tone Quality Recognition of Instruments Based on Multi-feature Fusion of Music Signal. Am. J. Netw. Commun. 2016, 5(2), 11-16. doi: 10.11648/j.ajnc.20160502.11
AMA Style
Zhe Lei, Mengying Ding, Xiaohong Guan, Youtian Du, Jicheng Feng, et al. Tone Quality Recognition of Instruments Based on Multi-feature Fusion of Music Signal. Am J Netw Commun. 2016;5(2):11-16. doi: 10.11648/j.ajnc.20160502.11
Share This Article
Twitter
Linked In
Facebook
Copy
Download@article{10.11648/j.ajnc.20160502.11,
author = {Zhe Lei and Mengying Ding and Xiaohong Guan and Youtian Du and Jicheng Feng and Qinping Gao and Zheng Liu},
title = {Tone Quality Recognition of Instruments Based on Multi-feature Fusion of Music Signal},
journal = {American Journal of Networks and Communications},
volume = {5},
number = {2},
pages = {11-16},
doi = {10.11648/j.ajnc.20160502.11},
url = {https://doi.org/10.11648/j.ajnc.20160502.11},
eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajnc.20160502.11},
abstract = {The traditional expert-based instrumental music evaluation strategy can’t meet the requirements of the rapidly accumulated audio data. The traditional strategy not only takes a high cost of human’s energy and time but also may have some problems on consistency and fairness of judgment. This paper aims at designing a complete recognition and evaluation strategy to automatically identify the timber of wind instruments. We take the clarinet as example and propose a strategy based on multi-feature fusion and random forest. First, we use the identification of fundamental frequency algorithm to automatically distinguish the notes performed by the instruments. Second, we extract 3 types of features including MFCC, brightness and roughness to describe the instrumental signals. Then, considering two kinds of variants: note and tone quality, we design 5 strategies to remove the influence of different notes in the evaluation of tone quality. By analyzing these strategies, we explore the optimal strategy for the recognition. The final evaluation results over 840 music slices demonstrate the effectiveness of this method.},
year = {2016}
}
TY - JOUR T1 - Tone Quality Recognition of Instruments Based on Multi-feature Fusion of Music Signal AU - Zhe Lei AU - Mengying Ding AU - Xiaohong Guan AU - Youtian Du AU - Jicheng Feng AU - Qinping Gao AU - Zheng Liu Y1 - 2016/04/19 PY - 2016 N1 - https://doi.org/10.11648/j.ajnc.20160502.11 DO - 10.11648/j.ajnc.20160502.11 T2 - American Journal of Networks and Communications JF - American Journal of Networks and Communications JO - American Journal of Networks and Communications SP - 11 EP - 16 PB - Science Publishing Group SN - 2326-8964 UR - https://doi.org/10.11648/j.ajnc.20160502.11 AB - The traditional expert-based instrumental music evaluation strategy can’t meet the requirements of the rapidly accumulated audio data. The traditional strategy not only takes a high cost of human’s energy and time but also may have some problems on consistency and fairness of judgment. This paper aims at designing a complete recognition and evaluation strategy to automatically identify the timber of wind instruments. We take the clarinet as example and propose a strategy based on multi-feature fusion and random forest. First, we use the identification of fundamental frequency algorithm to automatically distinguish the notes performed by the instruments. Second, we extract 3 types of features including MFCC, brightness and roughness to describe the instrumental signals. Then, considering two kinds of variants: note and tone quality, we design 5 strategies to remove the influence of different notes in the evaluation of tone quality. By analyzing these strategies, we explore the optimal strategy for the recognition. The final evaluation results over 840 music slices demonstrate the effectiveness of this method. VL - 5 IS - 2 ER -
Email: