Experiments and detailed error-analysis of automatic square notation transcription of medieval music manuscripts using CNN/LSTM-networks and a neume dictionary. Issue 1 (1st January 2021)

• Record Type: Journal Article
• Authors: Wick, C.; Puppe, F.
• Is Part Of: Journal of new music research. Volume 50:Issue 1(2021)
• Page Start: 18
• Page End: 36
• Publication Date: 2021-01-01
• Subjects: Optical music recognition -- historical document analysis -- medieval manuscripts -- neume notation -- CNN -- LSTM -- CTC; Music -- Periodicals; Musicology -- Periodicals; 780.72
• DOI: 10.1080/09298215.2021.1873393
• Languages: English
• ISSNs: 0929-8215

Abstract

Abstract : The automatic recognition of scanned Medieval manuscripts written in square notation still represents a challenge due to degradation, non-standard layouts, or notations. We propose to apply CNN/LSTM networks that are trained using the segmentation-free CTC-loss-function. For evaluation, we use three different manuscripts and achieve a diplomatic Symbol Accuracy Rate (dSAR) of 86.0% on the most difficult book and 92.2% on the cleanest one. A neume dictionary during decoding yields a relative improvement of about 5%. Finally, we perform a thorough error analysis to provide a deeper insight into problems of the algorithm.