Analyses of Kagura musical signals using LMS-based Fourier Analyzer

Abstract

Musical transcription requires much burden even for specialists in the musical field therefore, many trials of automatic transcription have been being done actively. As musical signals are substantially time varying, we have investigated an LMS-based Fourier analyzer to accommodate time varying characteristics. In this article, frequency response of the above adaptive algorithm is brief! reviewed in order to provide insight of the adaptive algorithm. And then, the analyzing system of Kagura Japanese folk music musical signals, which converts analyzed results to the MIDI format, is described. Finally, results in MIDI format are converted to musical scores by using commercially available software in order to verify the validity of the system.