TY  - CONF
AU  - Pau Torras
AU  - Arnau Baro
AU  - Alicia Fornes
AU  - Lei Kang
A2  - WoRMS
PY  - 2022//
TI  - Improving Handwritten Music Recognition through Language Model Integration
BT  - 4th International Workshop on Reading Music Systems (WoRMS2022)
SP  - 42
EP  - 46
KW  - optical music recognition
KW  - historical sources
KW  - diversity
KW  - music theory
KW  - digital humanities
N2  - 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.
L1  - http://refbase.cvc.uab.es/files/TBF2022.pdf
N1  - DAG; 600.121; 600.162; 602.230
ID  - Pau Torras2022
ER  -