Reading music is something a child can learn, and once understood, it becomes such a natural process that it is no longer a conscious efforE If we were to dissect this •natural process,' we might hypothesise that reading music is demmposed into tux:) parts: the visual recognition of graphical shapes; and the application of our musical knowledge to derive its meaning A computer paradigm that models this structure would be a v:sxon system connected to a knowledge base Imagine an Optical Music Recognition (ONIR) system where the user describes the simple graphical shapes found in music using a customised drawing package, and expresses the musical knowledge necessary to correctly interpret these simple graphical shapes, using a specially designed musical language Such a system would capture the essence of reading music, forming a versatile foundation Music is rich in its diversity of notatiom instruments include specialised markings in a score, for example bowing information for a violinist, and in extreme situations a score is presented using a substantially different notation style, for example guitar tablature Moreover, music notation is evolving, so even if were possible to completely capture all the primitive shapes used in music today, the set uould eventually become incomplete Such attributes emphasize the dynamic nature of the problem domain of OMR The describes] system meets such demands by allowing the user to specify 'what makes up music' Consequently the system is itself dynamie Let us now consider the proposed system in more detail, by studying the roles of the customised drawing package and specially designed musical language in turn Reading music is something a child can learn, and once understood, it becomes such a natural process that it is no longer a conscious efforE If we were to dissect this •natural process,' we might hypothesise that reading music is demmposed into tux:) parts: the visual recognition of graphical shapes; and the application of our musical knowledge to derive its meaning A computer paradigm that models this structure would be a v:sxon system connected to a knowledge base Imagine an Optical Music Recognition (ONIR) system where the user describes the simple graphical shapes found in music using a customised drawing package, and expresses the musical knowledge necessary to correctly interpret these simple graphical shapes, using a specially designed musical language Such a system would capture the essence of reading music, forming a versatile foundation Music is rich in its diversity of notatiom instruments include specialised markings in a score, for example bowing information for a violinist, and in extreme situations a score is presented using a substantially different notation style, for example guitar tablature Moreover, music notation is evolving, so even if were possible to completely capture all the primitive shapes used in music today, the set uould eventually become incomplete Such attributes emphasize the dynamic nature of the problem domain of OMR The describes] system meets such demands by allowing the user to specify 'what makes up music' Consequently the system is itself dynamie Let us now consider the proposed system in more detail, by studying the roles of the customised drawing package and specially designed musical language in turn