Matches in SemOpenAlex for { <https://semopenalex.org/work/W4304091720> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4304091720 abstract "Piano fingering is a creative and highly individualised task acquired by musicians progressively in their first music education years. Pianists must learn to choose the order of fingers to play the piano keys because scores do not have engraved finger and hand movements as other technique elements. Numerous research efforts have been conducted for automatic piano fingering based on a previous dataset composed of 150 score excerpts fully annotated by multiple expert annotators. However, most piano sheets include partial annotations for problematic finger and hand movements. We introduce a novel dataset for the task, the ThumbSet dataset, containing 2523 pieces with partial and noisy annotations of piano fingering crowdsourced from non-expert annotators. As part of our methodology, we propose two autoregressive neural networks with beam search decoding for modelling automatic piano fingering as a sequence-to-sequence learning problem, considering the correlation between output finger labels. We design the first model with the exact pitch representation of previous proposals. The second model uses graph neural networks to more effectively represent polyphony, whose treatment has been a common issue across previous studies. Finally, we finetune the models on the existing expert annotations dataset. The evaluation shows that (1) we are able to achieve high performance when training on the ThumbSet dataset and that (2) the proposed models outperform the state-of-the-art hidden Markov models and recurrent neural network baselines. Code, dataset, models, and results are made available to enhance the task reproducibility, including a new framework for evaluation." @default.
- W4304091720 created "2022-10-10" @default.
- W4304091720 creator A5006479715 @default.
- W4304091720 creator A5039915904 @default.
- W4304091720 creator A5043140898 @default.
- W4304091720 creator A5055794128 @default.
- W4304091720 creator A5071646953 @default.
- W4304091720 date "2022-10-10" @default.
- W4304091720 modified "2023-09-30" @default.
- W4304091720 title "Automatic Piano Fingering from Partially Annotated Scores using Autoregressive Neural Networks" @default.
- W4304091720 cites W1514829146 @default.
- W4304091720 cites W2127132706 @default.
- W4304091720 cites W2174276655 @default.
- W4304091720 cites W2183341477 @default.
- W4304091720 cites W2552810951 @default.
- W4304091720 cites W2560647685 @default.
- W4304091720 cites W2583498619 @default.
- W4304091720 cites W2890285072 @default.
- W4304091720 cites W2963459241 @default.
- W4304091720 cites W2998119150 @default.
- W4304091720 cites W3042609801 @default.
- W4304091720 cites W4226057428 @default.
- W4304091720 doi "https://doi.org/10.1145/3503161.3548372" @default.
- W4304091720 hasPublicationYear "2022" @default.
- W4304091720 type Work @default.
- W4304091720 citedByCount "1" @default.
- W4304091720 countsByYear W43040917202023 @default.
- W4304091720 crossrefType "proceedings-article" @default.
- W4304091720 hasAuthorship W4304091720A5006479715 @default.
- W4304091720 hasAuthorship W4304091720A5039915904 @default.
- W4304091720 hasAuthorship W4304091720A5043140898 @default.
- W4304091720 hasAuthorship W4304091720A5055794128 @default.
- W4304091720 hasAuthorship W4304091720A5071646953 @default.
- W4304091720 hasBestOaLocation W43040917202 @default.
- W4304091720 hasConcept C108583219 @default.
- W4304091720 hasConcept C119857082 @default.
- W4304091720 hasConcept C124086623 @default.
- W4304091720 hasConcept C142362112 @default.
- W4304091720 hasConcept C147168706 @default.
- W4304091720 hasConcept C149782125 @default.
- W4304091720 hasConcept C154945302 @default.
- W4304091720 hasConcept C159877910 @default.
- W4304091720 hasConcept C162324750 @default.
- W4304091720 hasConcept C187736073 @default.
- W4304091720 hasConcept C23224414 @default.
- W4304091720 hasConcept C2780451532 @default.
- W4304091720 hasConcept C28490314 @default.
- W4304091720 hasConcept C41008148 @default.
- W4304091720 hasConcept C50644808 @default.
- W4304091720 hasConcept C52119013 @default.
- W4304091720 hasConceptScore W4304091720C108583219 @default.
- W4304091720 hasConceptScore W4304091720C119857082 @default.
- W4304091720 hasConceptScore W4304091720C124086623 @default.
- W4304091720 hasConceptScore W4304091720C142362112 @default.
- W4304091720 hasConceptScore W4304091720C147168706 @default.
- W4304091720 hasConceptScore W4304091720C149782125 @default.
- W4304091720 hasConceptScore W4304091720C154945302 @default.
- W4304091720 hasConceptScore W4304091720C159877910 @default.
- W4304091720 hasConceptScore W4304091720C162324750 @default.
- W4304091720 hasConceptScore W4304091720C187736073 @default.
- W4304091720 hasConceptScore W4304091720C23224414 @default.
- W4304091720 hasConceptScore W4304091720C2780451532 @default.
- W4304091720 hasConceptScore W4304091720C28490314 @default.
- W4304091720 hasConceptScore W4304091720C41008148 @default.
- W4304091720 hasConceptScore W4304091720C50644808 @default.
- W4304091720 hasConceptScore W4304091720C52119013 @default.
- W4304091720 hasLocation W43040917201 @default.
- W4304091720 hasLocation W43040917202 @default.
- W4304091720 hasOpenAccess W4304091720 @default.
- W4304091720 hasPrimaryLocation W43040917201 @default.
- W4304091720 hasRelatedWork W2021413527 @default.
- W4304091720 hasRelatedWork W2168403679 @default.
- W4304091720 hasRelatedWork W3014300295 @default.
- W4304091720 hasRelatedWork W4223943233 @default.
- W4304091720 hasRelatedWork W4225161397 @default.
- W4304091720 hasRelatedWork W4312200629 @default.
- W4304091720 hasRelatedWork W4360585206 @default.
- W4304091720 hasRelatedWork W4364306694 @default.
- W4304091720 hasRelatedWork W4380075502 @default.
- W4304091720 hasRelatedWork W4380086463 @default.
- W4304091720 isParatext "false" @default.
- W4304091720 isRetracted "false" @default.
- W4304091720 workType "article" @default.