Parameter Optimization in Automatic Transcription of Music

Abstract

Based on former work on automatic transcription of musical time seriesinto sheet music (Ligges et al. (2002), Weihs and Ligges (2003, 2005))in this paper parameters of the transcription algorithm are optimizedfor various real singers. Moreover, the parameters of various artificialsinger models derived from the models of Rossignol et al. (1999)and Davy and Godsill (2002) are estimated. In both cases, optimizationis carried out by the Nelder-Mead (1965) search algorithm. In themodelling case a hierarchical Bayes extension is estimated by WinBUGS(Spiegelhalter et al. (2004)) as well. In all cases, optimal parametersare compared to heuristic estimates from our former standard method.