PT Unknown
AU Pau Torras
   Arnau Baro
   Alicia Fornes
   Lei Kang
TI Improving Handwritten Music Recognition through Language Model Integration
BT 4th International Workshop on Reading Music Systems (WoRMS2022)
PY 2022
BP 42
EP 46
DE optical music recognition; historical sources; diversity; music theory; digital humanities
AB Handwritten Music Recognition, especially in the historical domain, is an inherently challenging endeavour; paper degradation artefacts and the ambiguous nature of handwriting make recognising such scores an error-prone process, even for the current state-of-the-art Sequence to Sequence models. In this work we propose a way of reducing the production of statistically implausible output sequences by fusing a Language Model into a recognition Sequence to Sequence model. The idea is leveraging visually-conditioned and context-conditioned output distributions in order to automatically find and correct any mistakes that would otherwise break context significantly. We have found this approach to improve recognition results to 25.15 SER (%) from a previous best of 31.79 SER (%) in the literature.
ER