Zusammenfassung
This paper examines the automatic transcription of lyrics of Medieval music manuscripts by applying recent developments in the area of Automatic Text Recognition (ATR). We evaluate the performance of a CNN/LSTM-network on five different manuscripts dating from the 12th to 16<sup>th</sup> century and examine the impact of two different line segmentation approaches: Using an accurate manual segmentation yielded a Character Error Rate (CER) of up to 6.7% whereas 8.2% were reached on a fully automatic one. Furthermore, we propose an algorithm for the assignments of syllables to their respective neume by finding valid matches based on the positional output of the ATR. Depending on the ATR accuracy, an F<sub>1</sub>-score of over 99% was obtained.
Nutzer