{"id":"https://openalex.org/W4391760787","doi":"https://doi.org/10.1145/3632754.3632761","title":"Expressivity-aware Music Performance Retrieval using Mid-level Perceptual Features and Emotion Word Embeddings","display_name":"Expressivity-aware Music Performance Retrieval using Mid-level Perceptual Features and Emotion Word Embeddings","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4391760787","doi":"https://doi.org/10.1145/3632754.3632761"},"language":"en","primary_location":{"id":"doi:10.1145/3632754.3632761","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3632754.3632761","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3632754.3632761","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th Annual Meeting of the Forum for Information Retrieval Evaluation","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3632754.3632761","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043522798","display_name":"Shreyan Chowdhury","orcid":"https://orcid.org/0000-0003-1171-4036"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Shreyan Chowdhury","raw_affiliation_strings":["Johannes Kepler University, Austria"],"raw_orcid":"https://orcid.org/0000-0003-1171-4036","affiliations":[{"raw_affiliation_string":"Johannes Kepler University, Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003768123","display_name":"Gerhard Widmer","orcid":"https://orcid.org/0000-0003-3531-1282"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Gerhard Widmer","raw_affiliation_strings":["Johannes Kepler University, Austria"],"raw_orcid":"https://orcid.org/0000-0003-3531-1282","affiliations":[{"raw_affiliation_string":"Johannes Kepler University, Austria","institution_ids":["https://openalex.org/I121883995"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I121883995"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"73","last_page":"77"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10788","display_name":"Neuroscience and Music Perception","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7545970678329468},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5731817483901978},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5570018291473389},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5533280372619629},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5500478148460388},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5470621585845947},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5218112468719482},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5099798440933228},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.489208459854126},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.46112626791000366},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.4318329095840454},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41890886425971985},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14395764470100403},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08906888961791992},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0777631402015686}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7545970678329468},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5731817483901978},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5570018291473389},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5533280372619629},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5500478148460388},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5470621585845947},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5218112468719482},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5099798440933228},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.489208459854126},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.46112626791000366},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4318329095840454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41890886425971985},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14395764470100403},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08906888961791992},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0777631402015686},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3632754.3632761","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3632754.3632761","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3632754.3632761","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th Annual Meeting of the Forum for Information Retrieval Evaluation","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3632754.3632761","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3632754.3632761","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3632754.3632761","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th Annual Meeting of the Forum for Information Retrieval Evaluation","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1261784076","display_name":null,"funder_award_id":"670035","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G1808229388","display_name":null,"funder_award_id":"101019375","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7330785472","display_name":null,"funder_award_id":"101019375","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391760787.pdf"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W395933519","https://openalex.org/W2031767620","https://openalex.org/W2166345358","https://openalex.org/W2740887992","https://openalex.org/W2899990309","https://openalex.org/W2906259846","https://openalex.org/W3135367836","https://openalex.org/W3161754518","https://openalex.org/W3196974791","https://openalex.org/W4372259760"],"related_works":["https://openalex.org/W4251972423","https://openalex.org/W1503216044","https://openalex.org/W2393609567","https://openalex.org/W2369369044","https://openalex.org/W2354143083","https://openalex.org/W2372906645","https://openalex.org/W4319998713","https://openalex.org/W2081900870","https://openalex.org/W2366269494","https://openalex.org/W2050958351"],"abstract_inverted_index":{"This":[0],"paper":[1],"explores":[2],"a":[3,17,22,27,37,49,57,91,151,160],"specific":[4],"sub-task":[5],"of":[6,15,21,29,39,42,93,121,130],"cross-modal":[7,52,152],"music":[8,136],"retrieval.":[9],"We":[10,46],"consider":[11],"the":[12,43,78,82,101,112,128,166],"delicate":[13],"task":[14],"retrieving":[16],"performance":[18,89],"or":[19,34],"rendition":[20],"musical":[23,148],"piece":[24],"based":[25],"on":[26,90,111],"description":[28],"its":[30],"style,":[31],"expressive":[32],"character,":[33],"emotion":[35,138],"from":[36,135,143],"set":[38],"different":[40],"performances":[41,95],"same":[44],"piece.":[45],"observe":[47],"that":[48],"general":[50],"purpose":[51],"system":[53],"trained":[54],"to":[55,77],"learn":[56],"common":[58],"text-audio":[59],"embedding":[60],"space":[61],"does":[62],"not":[63],"yield":[64],"optimal":[65],"results":[66,126],"for":[67,162],"this":[68],"task.":[69],"By":[70],"introducing":[71,163],"two":[72],"changes":[73],"\u2013":[74,85],"one":[75],"each":[76],"text":[79,102,145],"encoder":[80,84],"and":[81,96,110,137,168],"audio":[83,113,123],"we":[86,104,115],"demonstrate":[87],"improved":[88],"dataset":[92],"piano":[94],"associated":[97],"free-text":[98],"descriptions.":[99],"On":[100],"side,":[103,114],"use":[105],"emotion-enriched":[106],"word":[107,140],"embeddings":[108,141],"(EWE)":[109],"extract":[116],"mid-level":[117,131,157],"perceptual":[118,132],"features":[119,133,158],"instead":[120],"generic":[122],"embeddings.":[124],"Our":[125],"highlight":[127],"effectiveness":[129],"learnt":[134,142],"enriched":[139],"emotion-labelled":[144],"in":[146,150,165],"capturing":[147],"expression":[149],"setting.":[153],"Additionally,":[154],"our":[155],"interpretable":[156],"provide":[159],"route":[161],"explainability":[164],"retrieval":[167],"downstream":[169],"recommendation":[170],"processes.":[171]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}