Low-Dimensional Feature Representation for Instrument Identification
Low-Dimensional Feature Representation for Instrument Identification
复制标题
DOI：
10.9746/jcmsi.5.249
复制
发表时间：
2012-07
期刊：
影响因子：
--
通讯作者：
Mizuki Ihara;S. Maeda;K. Ikeda;S. Ishii
中科院分区：
文献类型：
--
作者：
Mizuki Ihara;S. Maeda;K. Ikeda;S. Ishii
：对于单声道乐器识别，已经提出了各种特征提取和选择方法。仪器识别的问题之一是，由于记录条件的不同，即使在同一台仪器中也不一定能观察到相同的光谱。因此，找到非冗余的乐器特定特征非常重要，这些特征可以保留高质量乐器识别所必需的信息，从而将其应用于各种器乐分析。对于这种降维方法，作者提出使用线性投影方法：局部 Fisher 判别分析（LFDA）和 LFDA 结合主成分分析（PCA）。在通过实验澄清原始功率谱实际上有利于仪器分类后，作者通过 LFDA 或 PCA 后跟 LFDA (PCA-LFDA) 降低了特征维度。减少的特征实现了相当高的识别性能，与功率谱和其他现有研究所实现的识别性能相当或更高。这些结果表明，我们的 LFDA 和 PCA-LFDA 可以成功提取保持仪器特征信息的低维仪器特征。
: For monophonic music instrument identification, various feature extraction and selection methods have been proposed. One of the issues toward instrument identification is that the same spectrum is not always observed even in the same instrument due to the di ff erence of the recording condition. Therefore, it is important to find non-redundant instrument-specific features that maintain information essential for high-quality instrument identification to apply them to various instrumental music analyses. For such a dimensionality reduction method, the authors propose the utilization of linear projection methods: local Fisher discriminant analysis (LFDA) and LFDA combined with principal component analysis (PCA). After experimentally clarifying that raw power spectra are actually good for instrument classification, the authors reduced the feature dimensionality by LFDA or by PCA followed by LFDA (PCA-LFDA). The reduced features achieved reasonably high identification performance that was comparable or higher than those by the power spectra and those achieved by other existing studies. These results demonstrated that our LFDA and PCA-LFDA can successfully extract low-dimensional instrument features that maintain the characteristic information of the instruments.