Incorporating pitch class profiles for improving automatic transcription of Turkish makam music

In this paper we evaluate the impact of including knowledge about scale material into a system for the transcription of Turkish makam music. To this end, we extend our previously presented appoach by a refinement iteration that gives preference to note values present in the scale of the mode (i.e. makam). The information about the scalar material is provided in form of pitch class profiles, and they are imposed in form of a Dirichlet prior to our expanded probabilistic latent component analysis (PLCA) transcription system. While the inclusion of such a prior was supposed to focus the transcription system on musically meaningful areas, the obtained results are significantly improved only for recordings of certain instruments. In our discussion we demonstrate the quality of the obtained transcriptions, and discuss the difficulties caused for evaluation in the context of microtonal music.QC 20161031