{"id":"https://openalex.org/W4392904313","doi":"https://doi.org/10.1109/icassp48485.2024.10447564","title":"Unsupervised Pitch-Timbre Disentanglement of Musical Instruments Using a Jacobian Disentangled Sequential Autoencoder","display_name":"Unsupervised Pitch-Timbre Disentanglement of Musical Instruments Using a Jacobian Disentangled Sequential Autoencoder","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904313","doi":"https://doi.org/10.1109/icassp48485.2024.10447564"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/97925/2/Dixon%20Unsupervised%20Pitch-Timbre%202024%20Accepted.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029344951","display_name":"Yin-Jyun Luo","orcid":null},"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":true,"raw_author_name":"Yin-Jyun Luo","raw_affiliation_strings":["Queen Mary University of London,Centre for Digital Music","Centre for Digital Music, Queen Mary University of London"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digital Music","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001413512","display_name":"Sebastian Ewert","orcid":"https://orcid.org/0000-0002-0718-0476"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sebastian Ewert","raw_affiliation_strings":["Spotify"],"affiliations":[{"raw_affiliation_string":"Spotify","institution_ids":[]}]},{"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","Centre for Digital Music, Queen Mary University of London"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digital Music","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5029344951"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":0.7471,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65235316,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1036","last_page":"1040"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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":0.996999979019165,"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/autoencoder","display_name":"Autoencoder","score":0.9241425395011902},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.9044968485832214},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6624280214309692},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6140123009681702},{"id":"https://openalex.org/keywords/jacobian-matrix-and-determinant","display_name":"Jacobian matrix and determinant","score":0.6077300310134888},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5822486281394958},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4737069308757782},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.46656954288482666},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4536246657371521},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.4388481378555298},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42734187841415405},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37091052532196045},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27194827795028687},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.2291790246963501},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.21145117282867432}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.9241425395011902},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.9044968485832214},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6624280214309692},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6140123009681702},{"id":"https://openalex.org/C200331156","wikidata":"https://www.wikidata.org/wiki/Q506041","display_name":"Jacobian matrix and determinant","level":2,"score":0.6077300310134888},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5822486281394958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4737069308757782},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.46656954288482666},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4536246657371521},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.4388481378555298},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42734187841415405},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37091052532196045},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27194827795028687},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.2291790246963501},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.21145117282867432},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/97925","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/97925","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/97925/2/Dixon%20Unsupervised%20Pitch-Timbre%202024%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":null,"license_id":null,"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:123456789/97925","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/97925","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/97925/2/Dixon%20Unsupervised%20Pitch-Timbre%202024%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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"},"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392904313.pdf"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1613249581","https://openalex.org/W2161632835","https://openalex.org/W2619034550","https://openalex.org/W2758785877","https://openalex.org/W2759171953","https://openalex.org/W2962866891","https://openalex.org/W2972478942","https://openalex.org/W3016243847","https://openalex.org/W3034603995","https://openalex.org/W3101943858","https://openalex.org/W3127854286","https://openalex.org/W3175370919","https://openalex.org/W3208394868","https://openalex.org/W3210384560","https://openalex.org/W4225329057","https://openalex.org/W4312120832","https://openalex.org/W4319862209","https://openalex.org/W4372266019","https://openalex.org/W6640963894","https://openalex.org/W6738467200","https://openalex.org/W6741121127","https://openalex.org/W6745117592","https://openalex.org/W6756663807","https://openalex.org/W6757507232","https://openalex.org/W6764882207","https://openalex.org/W6784348365","https://openalex.org/W6788996426","https://openalex.org/W6803240769"],"related_works":["https://openalex.org/W2983142544","https://openalex.org/W2891059443","https://openalex.org/W4281663961","https://openalex.org/W3208888551","https://openalex.org/W4313561566","https://openalex.org/W3208386644","https://openalex.org/W4389832810","https://openalex.org/W4220682630","https://openalex.org/W3181622257","https://openalex.org/W3163146846"],"abstract_inverted_index":{"Disentangled":[0],"representation":[1],"learning":[2],"seeks":[3],"to":[4,81],"align":[5],"individual":[6],"dimensions":[7],"or":[8],"separate":[9],"groups":[10],"of":[11,13,18,52,78,88],"coordinates":[12],"latent":[14,25,82],"factors":[15,26],"with":[16],"attributes":[17],"observed":[19],"data":[20,54],"such":[21],"that":[22,40,64,74],"perturbing":[23],"certain":[24],"uniquely":[27],"changes":[28],"particular":[29],"attributes.":[30],"A":[31],"main":[32],"challenge":[33],"in":[34,97],"unsupervised":[35,102],"disentanglement":[36],"using":[37],"autoencoders":[38],"is":[39],"strong":[41],"regularisation,":[42],"while":[43],"necessary":[44],"for":[45],"consistent":[46],"disentanglement,":[47],"comes":[48],"at":[49],"the":[50,76],"expense":[51],"accurate":[53],"reconstruction.":[55],"To":[56],"address":[57],"this,":[58],"we":[59],"introduce":[60],"a":[61,66,71,94],"teacher-student":[62],"framework":[63],"incorporates":[65],"variational":[67],"sequential":[68],"autoencoder":[69],"and":[70,101],"Jacobian":[72],"constraint":[73],"regularises":[75],"variation":[77],"observations":[79],"relative":[80],"factors.":[83],"In":[84],"real-world":[85],"audio":[86],"recordings":[87],"musical":[89],"instruments,":[90],"our":[91],"approach":[92],"outperforms":[93],"state-of-the-art":[95],"method":[96],"both":[98],"sampling":[99],"quality":[100],"pitch-timbre":[103],"disentanglement.":[104]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
