{"id":"https://openalex.org/W4392911127","doi":"https://doi.org/10.1109/icassp48485.2024.10447670","title":"Towards Optimal Voice Disentanglement with Weak Supervision","display_name":"Towards Optimal Voice Disentanglement with Weak Supervision","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392911127","doi":"https://doi.org/10.1109/icassp48485.2024.10447670"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447670","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447670","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033902274","display_name":"Mohammad Izadi","orcid":"https://orcid.org/0000-0003-3561-3942"},"institutions":[{"id":"https://openalex.org/I76587968","display_name":"Bose (United States)","ror":"https://ror.org/0427k1a73","country_code":"US","type":"company","lineage":["https://openalex.org/I76587968"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Rasool Izadi","raw_affiliation_strings":["Bose Corporation,MA,USA","Bose Corporation, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bose Corporation,MA,USA","institution_ids":["https://openalex.org/I76587968"]},{"raw_affiliation_string":"Bose Corporation, MA, USA","institution_ids":["https://openalex.org/I76587968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089512820","display_name":"Yujia Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yujia Yan","raw_affiliation_strings":["University of Rochester,NY,USA","University of Rochester, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester,NY,USA","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"University of Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450332","display_name":"Shuo Zhang","orcid":"https://orcid.org/0000-0001-5197-6028"},"institutions":[{"id":"https://openalex.org/I76587968","display_name":"Bose (United States)","ror":"https://ror.org/0427k1a73","country_code":"US","type":"company","lineage":["https://openalex.org/I76587968"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuo Zhang","raw_affiliation_strings":["Bose Corporation,MA,USA","Bose Corporation, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bose Corporation,MA,USA","institution_ids":["https://openalex.org/I76587968"]},{"raw_affiliation_string":"Bose Corporation, MA, USA","institution_ids":["https://openalex.org/I76587968"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088641046","display_name":"Robert Louis Stevenson","orcid":"https://orcid.org/0000-0002-2701-8249"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Stevenson","raw_affiliation_strings":["University of Notre Dame,IN,USA","University of Notre Dame, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame,IN,USA","institution_ids":["https://openalex.org/I107639228"]},{"raw_affiliation_string":"University of Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0343488,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"10966","last_page":"10970"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9972000122070312,"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/T10860","display_name":"Speech and Audio Processing","score":0.9972000122070312,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9961000084877014,"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":0.5892841219902039},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3637380599975586}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5892841219902039},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3637380599975586}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447670","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447670","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.75}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2069870183","https://openalex.org/W2620364083","https://openalex.org/W2904922784","https://openalex.org/W2964812973","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2981628132","https://openalex.org/W2998249245","https://openalex.org/W3198858531","https://openalex.org/W3209059054","https://openalex.org/W4205848394","https://openalex.org/W4226219311","https://openalex.org/W4301371414","https://openalex.org/W4312529778","https://openalex.org/W4320892944","https://openalex.org/W4400188660","https://openalex.org/W6756663807","https://openalex.org/W6773762762","https://openalex.org/W6796577156","https://openalex.org/W6803547063","https://openalex.org/W6839738141","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Voice":[0],"disentanglement,":[1],"the":[2,100],"process":[3],"of":[4,102],"isolating":[5],"speech":[6,117,128],"or":[7],"singing":[8,96,109],"voice":[9,97,110],"into":[10],"several":[11],"latent":[12],"subspaces,":[13],"each":[14],"representing":[15],"certain":[16],"aspects,":[17],"holds":[18],"significant":[19],"importance":[20],"in":[21,88,105,123],"diverse":[22],"audio":[23],"processing":[24],"applications.":[25],"In":[26],"this":[27,37],"paper,":[28],"we":[29,74],"propose":[30],"an":[31],"efficient":[32],"weakly-supervised":[33,42],"approach":[34,52,104],"to":[35,58,80],"tackle":[36],"challenge.":[38],"Unlike":[39],"most":[40],"existing":[41],"methods":[43],"that":[44,76],"handle":[45],"fixed-length":[46],"sequences":[47,61],"and":[48,55,62,83],"single-rate":[49],"representations,":[50],"our":[51,89,103,120],"employs":[53],"transformers":[54],"variational":[56],"autoencoders":[57],"support":[59],"variable-length":[60],"multi-rate":[63],"representations.":[64,111],"Furthermore,":[65],"by":[66],"integrating":[67],"a":[68],"swapping":[69],"technique":[70],"for":[71,95,116],"paired":[72],"weak-supervision,":[73],"show":[75],"it":[77],"could":[78],"lead":[79],"optimal":[81,86],"disentanglement":[82,98],"demonstrate":[84],"its":[85],"efficacy":[87],"model.":[90],"Experimental":[91],"evaluation":[92],"on":[93,114],"VocalSet":[94],"shows":[99],"superiority":[101],"finding":[106],"more":[107],"disentangled":[108],"Similarly,":[112],"tests":[113],"LibriSpeech":[115],"recognition":[118],"highlight":[119],"method's":[121],"effectiveness":[122],"removing":[124],"speaker":[125],"information":[126],"from":[127],"content.":[129]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}