{"id":"https://openalex.org/W3208394868","doi":"https://doi.org/10.24963/ijcai.2022/458","title":"Towards Robust Unsupervised Disentanglement of Sequential Data \u2014 A Case Study Using Music Audio","display_name":"Towards Robust Unsupervised Disentanglement of Sequential Data \u2014 A Case Study Using Music Audio","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W3208394868","doi":"https://doi.org/10.24963/ijcai.2022/458","mag":"3208394868"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/458","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/458","pdf_url":"https://www.ijcai.org/proceedings/2022/0458.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2022/0458.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":false,"raw_author_name":"Yin-Jyun Luo","raw_affiliation_strings":["Queen Mary University of London","Centre for Digital Music, Queen Mary University of London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Spotify","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053652066","display_name":"Simon Dixon","orcid":"https://orcid.org/0000-0002-8886-7666"},"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, Queen Mary University of London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London","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":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6443,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.77286888,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3299","last_page":"3305"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9993000030517578,"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"}},{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7990913391113281},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7694599032402039},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.7319200038909912},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5829967856407166},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5239234566688538},{"id":"https://openalex.org/keywords/latent-variable-model","display_name":"Latent variable model","score":0.47039660811424255},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.46682921051979065},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4645281732082367},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4271397888660431}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7990913391113281},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7694599032402039},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.7319200038909912},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5829967856407166},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5239234566688538},{"id":"https://openalex.org/C65965080","wikidata":"https://www.wikidata.org/wiki/Q1806885","display_name":"Latent variable model","level":3,"score":0.47039660811424255},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.46682921051979065},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4645281732082367},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4271397888660431},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.24963/ijcai.2022/458","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/458","pdf_url":"https://www.ijcai.org/proceedings/2022/0458.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/84772","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/84772","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/84772/2/Dixon%20Towards%20Robust%20Unsupervised%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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/79686","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/79686","pdf_url":null,"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":null}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/458","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/458","pdf_url":"https://www.ijcai.org/proceedings/2022/0458.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3208394868.pdf","grobid_xml":"https://content.openalex.org/works/W3208394868.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1613249581","https://openalex.org/W1959608418","https://openalex.org/W2049934117","https://openalex.org/W2126776273","https://openalex.org/W2161632835","https://openalex.org/W2530846021","https://openalex.org/W2758785877","https://openalex.org/W2890679110","https://openalex.org/W2908118172","https://openalex.org/W2937090315","https://openalex.org/W2946619602","https://openalex.org/W2950662112","https://openalex.org/W2952161038","https://openalex.org/W2962820691","https://openalex.org/W2962866891","https://openalex.org/W2970912396","https://openalex.org/W2979429887","https://openalex.org/W2981396729","https://openalex.org/W2985924367","https://openalex.org/W2997790181","https://openalex.org/W3005066471","https://openalex.org/W3007727789","https://openalex.org/W3013223143","https://openalex.org/W3013816534","https://openalex.org/W3034603995","https://openalex.org/W3034875137","https://openalex.org/W3045863681","https://openalex.org/W3080587002","https://openalex.org/W3082960758","https://openalex.org/W3097059217","https://openalex.org/W3100972534","https://openalex.org/W3101943858","https://openalex.org/W3122011104","https://openalex.org/W3127854286","https://openalex.org/W3132648081","https://openalex.org/W3157533728","https://openalex.org/W3175370919","https://openalex.org/W3176908974","https://openalex.org/W3210384560","https://openalex.org/W4362724041"],"related_works":["https://openalex.org/W2461917396","https://openalex.org/W2037497866","https://openalex.org/W4243467573","https://openalex.org/W62001224","https://openalex.org/W1502435251","https://openalex.org/W3032390039","https://openalex.org/W1584341211","https://openalex.org/W3122667150","https://openalex.org/W3145681568","https://openalex.org/W4393387622"],"abstract_inverted_index":{"Disentangled":[0],"sequential":[1],"autoencoders":[2],"(DSAEs)":[3],"represent":[4],"a":[5,21,30,97,102,142],"class":[6],"of":[7,54,77,82,145,179],"probabilistic":[8],"graphical":[9],"models":[10],"that":[11,66,106],"describes":[12],"an":[13,47],"observed":[14],"sequence":[15],"with":[16],"dynamic":[17,84],"latent":[18,23,85,94],"variables":[19],"and":[20,50,58,80,87,120,133,163,170,184],"static":[22,93],"variable.":[24,95],"The":[25,127],"former":[26],"encode":[27],"information":[28],"at":[29],"frame":[31],"rate":[32],"identical":[33],"to":[34,74,90,116,124,173],"the":[35,38,42,55,67,75,83,92,118,136],"observation,":[36],"while":[37],"latter":[39],"globally":[40],"governs":[41],"entire":[43],"sequence.":[44],"This":[45],"introduces":[46],"inductive":[48],"bias":[49],"facilitates":[51],"unsupervised":[52,132],"disentanglement":[53,180],"underlying":[56],"local":[57],"global":[59,137],"factors.":[60],"In":[61],"this":[62],"paper,":[63],"we":[64,99],"show":[65],"vanilla":[68],"DSAE":[69],"suffers":[70],"from":[71],"being":[72],"sensitive":[73],"choice":[76],"model":[78,119,146],"architecture":[79],"capacity":[81],"variables,":[86],"is":[88,130],"prone":[89],"collapse":[91,139],"As":[96],"countermeasure,":[98],"propose":[100],"TS-DSAE,":[101],"two-stage":[103],"training":[104,156],"framework":[105,129],"first":[107],"learns":[108],"sequence-level":[109],"prior":[110],"distributions,":[111],"which":[112,157],"are":[113],"subsequently":[114],"employed":[115],"regularise":[117],"facilitate":[121],"auxiliary":[122],"objectives":[123],"promote":[125],"disentanglement.":[126],"proposed":[128],"fully":[131],"robust":[134],"against":[135],"factor":[138],"problem":[140],"across":[141],"wide":[143],"range":[144],"configurations.":[147],"It":[148],"also":[149],"avoids":[150],"typical":[151],"solutions":[152],"such":[153],"as":[154],"adversarial":[155],"usually":[158],"involves":[159],"laborious":[160],"parameter":[161],"tuning,":[162],"domain-specific":[164],"data":[165],"augmentation.":[166],"We":[167],"conduct":[168],"quantitative":[169],"qualitative":[171],"evaluations":[172],"demonstrate":[174],"its":[175],"robustness":[176],"in":[177],"terms":[178],"on":[181],"both":[182],"artificial":[183],"real-world":[185],"music":[186],"audio":[187],"datasets.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}