Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386593591> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4386593591 abstract "Sound retrieval for assisted music composition depends on evaluating similarity between musical instrument sounds, which is partly influenced by playing techniques. Previous methods utilizing Euclidean nearest neighbours over acoustic features show some limitations in retrieving sounds sharing equivalent timbral properties, but potentially generated using a different instrument, playing technique, pitch or dynamic. In this paper, we present a metric learning system designed to approximate human similarity judgments between extended musical playing techniques using graph neural networks. Such structure is a natural candidate for solving similarity retrieval tasks, yet have seen little application in modelling perceptual music similarity. We optimize a Graph Convolutional Network (GCN) over acoustic features via a proxy metric learning loss to learn embeddings that reflect perceptual similarities. Specifically, we construct the graph’s adjacency matrix from the acoustic data manifold with an example-wise adaptive k-nearest neighbourhood graph: Adaptive Neighbourhood Graph Neural Network (AN-GNN). Our approach achieves 96.4% retrieval accuracy compared to 38.5% with a Euclidean metric and 86.0% with a multilayer perceptron (MLP), while effectively considering retrievals from distinct playing techniques to the query example." @default.
- W4386593591 created "2023-09-12" @default.
- W4386593591 creator A5005866826 @default.
- W4386593591 creator A5027304029 @default.
- W4386593591 creator A5029522748 @default.
- W4386593591 creator A5032485940 @default.
- W4386593591 creator A5060724782 @default.
- W4386593591 creator A5084672392 @default.
- W4386593591 creator A5091632784 @default.
- W4386593591 date "2023-10-22" @default.
- W4386593591 modified "2023-10-12" @default.
- W4386593591 title "Perceptual Musical Similarity Metric Learning with Graph Neural Networks" @default.
- W4386593591 cites W2619697695 @default.
- W4386593591 cites W2888806961 @default.
- W4386593591 cites W2939574508 @default.
- W4386593591 cites W2945837706 @default.
- W4386593591 cites W2963775347 @default.
- W4386593591 cites W2979750740 @default.
- W4386593591 cites W2990045899 @default.
- W4386593591 cites W3015829441 @default.
- W4386593591 cites W3034202663 @default.
- W4386593591 cites W3097934054 @default.
- W4386593591 cites W3109975354 @default.
- W4386593591 cites W3111213250 @default.
- W4386593591 cites W3122049989 @default.
- W4386593591 cites W4290043985 @default.
- W4386593591 cites W4312562773 @default.
- W4386593591 cites W4386589137 @default.
- W4386593591 doi "https://doi.org/10.1109/waspaa58266.2023.10248151" @default.
- W4386593591 hasPublicationYear "2023" @default.
- W4386593591 type Work @default.
- W4386593591 citedByCount "0" @default.
- W4386593591 crossrefType "proceedings-article" @default.
- W4386593591 hasAuthorship W4386593591A5005866826 @default.
- W4386593591 hasAuthorship W4386593591A5027304029 @default.
- W4386593591 hasAuthorship W4386593591A5029522748 @default.
- W4386593591 hasAuthorship W4386593591A5032485940 @default.
- W4386593591 hasAuthorship W4386593591A5060724782 @default.
- W4386593591 hasAuthorship W4386593591A5084672392 @default.
- W4386593591 hasAuthorship W4386593591A5091632784 @default.
- W4386593591 hasBestOaLocation W43865935912 @default.
- W4386593591 hasConcept C103278499 @default.
- W4386593591 hasConcept C110484373 @default.
- W4386593591 hasConcept C11413529 @default.
- W4386593591 hasConcept C115961682 @default.
- W4386593591 hasConcept C120174047 @default.
- W4386593591 hasConcept C132525143 @default.
- W4386593591 hasConcept C153180895 @default.
- W4386593591 hasConcept C154945302 @default.
- W4386593591 hasConcept C179717631 @default.
- W4386593591 hasConcept C180356752 @default.
- W4386593591 hasConcept C28490314 @default.
- W4386593591 hasConcept C41008148 @default.
- W4386593591 hasConcept C50644808 @default.
- W4386593591 hasConcept C80444323 @default.
- W4386593591 hasConcept C81363708 @default.
- W4386593591 hasConceptScore W4386593591C103278499 @default.
- W4386593591 hasConceptScore W4386593591C110484373 @default.
- W4386593591 hasConceptScore W4386593591C11413529 @default.
- W4386593591 hasConceptScore W4386593591C115961682 @default.
- W4386593591 hasConceptScore W4386593591C120174047 @default.
- W4386593591 hasConceptScore W4386593591C132525143 @default.
- W4386593591 hasConceptScore W4386593591C153180895 @default.
- W4386593591 hasConceptScore W4386593591C154945302 @default.
- W4386593591 hasConceptScore W4386593591C179717631 @default.
- W4386593591 hasConceptScore W4386593591C180356752 @default.
- W4386593591 hasConceptScore W4386593591C28490314 @default.
- W4386593591 hasConceptScore W4386593591C41008148 @default.
- W4386593591 hasConceptScore W4386593591C50644808 @default.
- W4386593591 hasConceptScore W4386593591C80444323 @default.
- W4386593591 hasConceptScore W4386593591C81363708 @default.
- W4386593591 hasFunder F4320311061 @default.
- W4386593591 hasFunder F4320314731 @default.
- W4386593591 hasFunder F4320334627 @default.
- W4386593591 hasLocation W43865935911 @default.
- W4386593591 hasLocation W43865935912 @default.
- W4386593591 hasOpenAccess W4386593591 @default.
- W4386593591 hasPrimaryLocation W43865935911 @default.
- W4386593591 hasRelatedWork W2043165415 @default.
- W4386593591 hasRelatedWork W2374780422 @default.
- W4386593591 hasRelatedWork W2410198229 @default.
- W4386593591 hasRelatedWork W2767651786 @default.
- W4386593591 hasRelatedWork W2912288872 @default.
- W4386593591 hasRelatedWork W2974128303 @default.
- W4386593591 hasRelatedWork W3027599074 @default.
- W4386593591 hasRelatedWork W3164306936 @default.
- W4386593591 hasRelatedWork W3194558310 @default.
- W4386593591 hasRelatedWork W4287178724 @default.
- W4386593591 isParatext "false" @default.
- W4386593591 isRetracted "false" @default.
- W4386593591 workType "article" @default.