{"id":"https://openalex.org/W4372266019","doi":"https://doi.org/10.1109/icassp49357.2023.10095009","title":"Disentangling the Horowitz Factor: Learning Content and Style From Expressive Piano Performance","display_name":"Disentangling the Horowitz Factor: Learning Content and Style From Expressive Piano Performance","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266019","doi":"https://doi.org/10.1109/icassp49357.2023.10095009"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/88841/2/Dixon%20Disentangling%20the%20Horowitz%202023%20Accepted.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100356958","display_name":"Huan Zhang","orcid":"https://orcid.org/0000-0002-3698-5409"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Huan Zhang","raw_affiliation_strings":["Queen Mary University of London,Centre for Digital Music,UK","Centre for Digital Music, Queen Mary University of London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digital Music,UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077484271","display_name":"Simon Dixon","orcid":"https://orcid.org/0000-0002-6098-481X"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon Dixon","raw_affiliation_strings":["Queen Mary University of London,Centre for Digital Music,UK","Centre for Digital Music, Queen Mary University of London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digital Music,UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, UK","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10788","display_name":"Neuroscience and Music Perception","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10788","display_name":"Neuroscience and Music Perception","score":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9986000061035156,"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/piano","display_name":"Piano","score":0.8558169603347778},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.7539860010147095},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.7317336201667786},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5873730182647705},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.48455610871315},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45987361669540405},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40441352128982544},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37837207317352295},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.25915277004241943},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1731165647506714},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.16393905878067017},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.11045804619789124},{"id":"https://openalex.org/keywords/art-history","display_name":"Art history","score":0.062477946281433105}],"concepts":[{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.8558169603347778},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.7539860010147095},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.7317336201667786},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5873730182647705},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.48455610871315},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45987361669540405},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40441352128982544},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37837207317352295},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.25915277004241943},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1731165647506714},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.16393905878067017},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.11045804619789124},{"id":"https://openalex.org/C52119013","wikidata":"https://www.wikidata.org/wiki/Q50637","display_name":"Art history","level":1,"score":0.062477946281433105},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/88841","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/88841","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/88841/2/Dixon%20Disentangling%20the%20Horowitz%202023%20Accepted.pdf","source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"}],"best_oa_location":{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/88841","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/88841","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/88841/2/Dixon%20Disentangling%20the%20Horowitz%202023%20Accepted.pdf","source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/10"},{"display_name":"Peace, Justice and strong institutions","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4372266019.pdf"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W395933519","https://openalex.org/W1498052334","https://openalex.org/W2014495794","https://openalex.org/W2135810348","https://openalex.org/W2560674852","https://openalex.org/W2615497679","https://openalex.org/W2752796333","https://openalex.org/W2758785877","https://openalex.org/W2799097967","https://openalex.org/W2810979309","https://openalex.org/W2811079561","https://openalex.org/W2901791883","https://openalex.org/W2954914497","https://openalex.org/W2963799213","https://openalex.org/W2963873275","https://openalex.org/W2964706117","https://openalex.org/W2986779468","https://openalex.org/W3015212100","https://openalex.org/W3104832546","https://openalex.org/W3127854286","https://openalex.org/W3175663427","https://openalex.org/W3197103763","https://openalex.org/W3208394868","https://openalex.org/W4225329057","https://openalex.org/W6629855375","https://openalex.org/W6631643160","https://openalex.org/W6679962959","https://openalex.org/W6728271538","https://openalex.org/W6745117592","https://openalex.org/W6746090280","https://openalex.org/W6746767065","https://openalex.org/W6752051073","https://openalex.org/W6753018729","https://openalex.org/W6762214719","https://openalex.org/W6764882207","https://openalex.org/W6782602824","https://openalex.org/W6799235175","https://openalex.org/W6839738141","https://openalex.org/W6847094994"],"related_works":["https://openalex.org/W2316271602","https://openalex.org/W2357375963","https://openalex.org/W607893370","https://openalex.org/W629160228","https://openalex.org/W584653787","https://openalex.org/W4362512397","https://openalex.org/W587444722","https://openalex.org/W2022713566","https://openalex.org/W2336023324","https://openalex.org/W2356684049"],"abstract_inverted_index":{"In":[0,45],"the":[1,15,32,36,79,107,125,139,164,174,181],"Western":[2],"art":[3],"music":[4],"tradition,":[5],"expressive":[6,64],"piano":[7,65,117],"performance":[8,61],"consists":[9],"of":[10,13,35,78,113,186],"two":[11],"kinds":[12],"information:":[14],"score,":[16,37],"with":[17,27,84,91,119,163,167,183],"pitch":[18,151],"and":[19,31,43,60,87,97,103,123,128,152,155,173],"timing":[20],"expressed":[21],"in":[22,40,67,131],"simple":[23],"musical":[24,58,147],"units":[25],"along":[26,90],"occasional":[28],"expression":[29],"instructions,":[30],"performer\u2019s":[33],"interpretation":[34],"involving":[38],"variations":[39],"tempo,":[41],"dynamics":[42],"articulation.":[44],"this":[46],"paper,":[47],"we":[48],"present":[49],"a":[50,110,132],"novel":[51],"framework":[52],"for":[53],"learning":[54],"representations":[55],"that":[56,138,145],"disentangle":[57],"content":[59,86,126,148,165],"style":[62,88,129,176],"from":[63],"performances":[66,118],"an":[68,76],"unsupervised":[69],"manner.":[70,134],"Our":[71,135],"method":[72],"is":[73],"based":[74],"on":[75,106],"extension":[77],"vector-quantized":[80],"variational":[81],"autoencoder":[82],"(VQ-VAE)":[83],"individual":[85],"branches,":[89],"mutual":[92],"information":[93],"(MI)":[94],"minimization":[95],"techniques":[96],"self-supervising":[98],"strategies.":[99],"We":[100],"performed":[101],"experiments":[102,136],"ablation":[104],"studies":[105],"ATEPP":[108],"dataset,":[109],"large":[111],"set":[112],"automatically":[114],"transcribed":[115],"virtuosic":[116],"rich":[120],"stylistic":[121,156],"variations,":[122],"evaluated":[124],"reconstruction":[127],"discrimination":[130,177],"style-transfer":[133],"demonstrate":[137],"model":[140],"learnt":[141],"separate":[142],"latent":[143],"variables":[144],"encode":[146],"(such":[149],"as":[150,158],"relative":[153],"timing)":[154],"attributes,":[157],"generated":[159],"samples":[160],"align":[161],"well":[162],"input":[166],"low":[168],"note":[169],"error":[170],"rates":[171],"(NER),":[172],"40-way":[175],"proxy":[178],"task":[179],"outperformed":[180],"baseline":[182],"top1":[184],"accuracy":[185],"0.168.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}