Error prooving and sensorimotor feedback for singing voice

Abstract

This paper presents a sensorimotor system for Byzantine Music. The main goal of this research is to detect some pre-defined errors in singing performance. After error-detection, the system uses a pre-defined error-dictionary in order to feedback. Through these feedbacks the potential chanter is being able to correct his performance. The system is being trained via experts MFCC features from a corpus of anthems. The recognition also takes place via MFCC but form student. The developed system is being able to evaluate in real time the pitch distance and furthermore the duration of two musician's performances, expert and student. The system may also evaluate the distance between two sequential musical gestures by which we may find the tempo of the hymn. After the pitch of these two hymns are being compared any identified errors will cause a feedback action to the student. This feedback corresponds to an error dictionary.