{"id":"https://openalex.org/W4392909504","doi":"https://doi.org/10.1109/icassp48485.2024.10447835","title":"Posterior Variance-Parameterised Gaussian Dropout: Improving Disentangled Sequential Autoencoders for Zero-Shot Voice Conversion","display_name":"Posterior Variance-Parameterised Gaussian Dropout: Improving Disentangled Sequential Autoencoders for Zero-Shot Voice Conversion","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909504","doi":"https://doi.org/10.1109/icassp48485.2024.10447835"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447835","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447835","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/97926/2/Dixon%20Posterior%20Variance-Parameterised%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":false,"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"],"raw_orcid":null,"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":"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"],"raw_orcid":null,"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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":0.3314,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.46397338,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"11676","last_page":"11680"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9979000091552734,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9979000091552734,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9902999997138977,"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/T11309","display_name":"Music and Audio Processing","score":0.9164999723434448,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.7726739048957825},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.6276481747627258},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.6030993461608887},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6018748879432678},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5811238884925842},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4521879255771637},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.44728392362594604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35408294200897217},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.18614420294761658},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10655537247657776},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.05760538578033447}],"concepts":[{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.7726739048957825},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.6276481747627258},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6030993461608887},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6018748879432678},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5811238884925842},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4521879255771637},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.44728392362594604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35408294200897217},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.18614420294761658},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10655537247657776},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.05760538578033447},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447835","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447835","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:123456789/97926","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/97926","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/97926/2/Dixon%20Posterior%20Variance-Parameterised%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:123456789/97926","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/97926","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/97926/2/Dixon%20Posterior%20Variance-Parameterised%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":[{"id":"https://metadata.un.org/sdg/10","score":0.6499999761581421,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392909504.pdf","grobid_xml":"https://content.openalex.org/works/W4392909504.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W2046056978","https://openalex.org/W2094721231","https://openalex.org/W2163922914","https://openalex.org/W2603777577","https://openalex.org/W2752796333","https://openalex.org/W2937090315","https://openalex.org/W2972659941","https://openalex.org/W2972894903","https://openalex.org/W3015434413","https://openalex.org/W3095361818","https://openalex.org/W3143523927","https://openalex.org/W3163475957","https://openalex.org/W3168719651","https://openalex.org/W3197103763","https://openalex.org/W3197659778","https://openalex.org/W3198034710","https://openalex.org/W3208394868","https://openalex.org/W4224929761","https://openalex.org/W4225329057","https://openalex.org/W4287889585","https://openalex.org/W4319862209","https://openalex.org/W4390912444","https://openalex.org/W6601425427","https://openalex.org/W6637108112","https://openalex.org/W6638116569","https://openalex.org/W6640963894","https://openalex.org/W6674330103","https://openalex.org/W6729906282","https://openalex.org/W6745117592","https://openalex.org/W6747620207","https://openalex.org/W6752888775","https://openalex.org/W6755135894","https://openalex.org/W6755300632","https://openalex.org/W6757140150","https://openalex.org/W6762533536","https://openalex.org/W6764882207","https://openalex.org/W6790622591","https://openalex.org/W6803240769"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W3082178636","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2782041652","https://openalex.org/W2366718574","https://openalex.org/W2090422802"],"abstract_inverted_index":{"The":[0],"class":[1],"of":[2,23,40,81,112,135],"disentangled":[3],"sequential":[4],"auto-encoders":[5],"factorises":[6],"speech":[7],"into":[8],"time-invariant":[9],"(global)":[10],"and":[11,18,89,126,140],"time-variant":[12],"(local)":[13],"representations":[14,59],"for":[15],"speaker":[16,38,131,136],"identity":[17],"linguistic":[19,51],"content,":[20],"respectively.":[21],"Many":[22],"the":[24,50,57,63,76,82,99,110,113,123],"existing":[25,118],"models":[26,121],"employ":[27],"this":[28],"assumption":[29],"to":[30,44,67,70,98,108],"tackle":[31],"zero-shot":[32,119],"voice":[33],"conversion":[34,132],"(VC),":[35],"which":[36],"converts":[37],"characteristics":[39],"any":[41,45],"given":[42],"utterance":[43],"novel":[46],"speakers":[47],"while":[48],"preserving":[49],"content.":[52],"However,":[53],"balancing":[54],"capacity":[55,74],"between":[56],"two":[58],"is":[60],"intricate,":[61],"as":[62],"global":[64,114],"representation":[65,101],"tends":[66],"collapse":[68],"due":[69],"its":[71],"lower":[72],"information":[73,96],"along":[75],"time":[77],"axis":[78],"than":[79],"that":[80,93],"local":[83,100],"representation.":[84],"We":[85,116],"propose":[86],"a":[87],"simple":[88],"effective":[90],"dropout":[91],"technique":[92],"applies":[94],"an":[95],"bottleneck":[97],"via":[102],"multiplicative":[103],"Gaussian":[104],"noise,":[105],"in":[106,130,133,146],"order":[107],"encourage":[109],"usage":[111],"one.":[115],"endow":[117],"VC":[120],"with":[122],"proposed":[124],"method":[125],"show":[127],"significant":[128],"improvements":[129],"terms":[134],"verification":[137],"acceptance":[138],"rate":[139],"comparable":[141],"or":[142],"better":[143],"intelligibility":[144],"measured":[145],"character":[147],"error":[148],"rate.":[149]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}