Lyric Extraction and Recognition on Digital Images of Early Music Sources

Optical music recognition (OMR) is one of the most promising tools for generating large-scale, distributable libraries of musical data. Much OMR work has focussed on instrumental music, avoiding a special challenge vocal music poses for OMR: lyric recognition. Lyrics complicate the page layout, making it more difficult to identify the regions of the page that carry musical notation. Furthermore, users expect a complete OMR process for vocal music to include recognition of the lyrics, reunification of syllables when they have been separated, and alignment of these lyrics with the recognised music. Unusual layouts and inconsistent practises for syllabification, however, make lyric recognition more challenging than traditional optical character recognition (OCR). This paper surveys historical approaches to lyric recognition, outlines open challenges, and presents a new approach to extracting text lines in medieval manuscripts, one of the frontiers of OMR research today.