An Auditory Model Based Transcriber of Singing Sequences

TLDR: A new system for the automatic transcription of singing sequences into a sequence of pitch and duration pairs is presented and it is shown that the accuracy of the newly proposed transcription system is not very to the choice of the free parameters, at least as long as they remain in the vicinity of the values one could forecast on the basis of their meaning.

Abstract: In this paper, a new system for the automatic transcription of singing sequences into a sequence of pitch and duration pairs is presented. Although such a system may have a wider range of applications, it was mainly developed to become the acoustic module of a queryby-humming (QBH) system for retrieving pieces of music from a digitized musical library. The first part of the paper is devoted to the systematic evaluation of a variety of state-of-the art transcription systems. The main result of this evaluation is that there is clearly a need for more accurate systems. Especially the segmentation was experienced as being too error prone ( % segmentation errors). In the second part of the paper, a new auditory model based transcription system is proposed and evaluated. The results of that evaluation are very promising. Segmentation errors vary between 0 and 7 %, dependent on the amount of lyrics that is used by the singer. The paper ends with the description of an experimental study that was issued to demonstrate that the accuracy of the newly proposed transcription system is not very sensitive to the choice of the free parameters, at least as long as they remain in the vicinity of the values one could forecast on the basis of their meaning.