期刊名称：International Journal on Electrical Engineering and Informatics
印刷版ISSN：2085-6830
出版年度：2018
卷号：10
期号：4
页码：753-764
DOI：10.15676/ijeei.2018.10.4.9
出版社：School of Electrical Engineering and Informatics
摘要：This paper proposes a feature extraction method for a chord recognition, whichgives a fewer number of feature extraction coefficients than the previous works. The methodof the proposed feature extraction is segment averaging with SHPS (Simplified HarmonicProduct Spectrum) and logarithmic scaling. The chords used in developing the proposedfeature extraction were guitar chords. In a more detail, the method of the proposed featureextraction basically is as follows. Firstly, the input signal is transformed using FFT (FastFourier Transform). Secondly, the left portion of the transformed signal is then processed insuccession using SHPS, logarithmic scaling, and segment averaging. The output of segmentaveraging is the result of the proposed feature extraction. Based on the test results, theproposed feature extraction is quite efficient for use in chord recognition, since it requiresonly at least eight coefficients to represent each chord.
