THURSDAY, MARCH 22, 2012

Christopher Raphael, Department of Informatics

"Large-Scale Optical Music Recognition on the International Music Score Library Project"

Vast quantities of character-encoded text form the foundation for the Information Retrieval revolution of recent decades, allowing the automatic search, analysis and categorization of text. In contrast, very little symbolically-represent music exists, preventing music from fully participating in the Information Age. The International Music Score Library Project (IMSLP) is a large and rapidly growing open library of public domain machine-printed classical music scores, actively used by many musicians, music scholars, and researchers around the world. In this presentation, Dr. Raphael will discuss his ongoing work in developing an optical music recognition (OMR) system, specifically designed for the needs of the IMSLP, capable of transforming the library's score images into symbolic representations.

The ultimate fruit of this work, large-scale symbolic music databases, would transform the musical landscape allowing broad and instant access to public domain music, important commercial applications such as digital music stands, and would form the basis for many new directions in Music Informatics and Computational Musicology. A successful effort here will require significant improvement in the state of the art for Optical Music Recognition, though the problem may not be solved by science alone. The complexity and ambiguity of music notation will require the input of knowledgeable users to assist the automatic recognition process. Thus, part of the challenge involves designing efficient ways to combine automatic recognition with human guidance. The proposed technology seeks to bring the IMSLP community together in a Wikipedia-like collaboration to mine this invaluable resource.

• Audio & Powerpoint of Presentation: