{"id":"https://openalex.org/W4406461892","doi":"https://doi.org/10.1109/slt61566.2024.10832297","title":"Discrete Unit Based Masking For Improving Disentanglement in Voice Conversion","display_name":"Discrete Unit Based Masking For Improving Disentanglement in Voice Conversion","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461892","doi":"https://doi.org/10.1109/slt61566.2024.10832297"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832297","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832297","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","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/A5100354178","display_name":"Peter Lee","orcid":"https://orcid.org/0000-0002-3898-8881"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Philip H. Lee","raw_affiliation_strings":["The University of Texas at Dallas,Speech & Machine Learning (SML) Lab,USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Speech & Machine Learning (SML) Lab,USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018311726","display_name":"\u0130smail Rasim \u00dclgen","orcid":"https://orcid.org/0000-0003-4593-9057"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ismail Rasim Ulgen","raw_affiliation_strings":["The University of Texas at Dallas,Speech & Machine Learning (SML) Lab,USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Speech & Machine Learning (SML) Lab,USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001303929","display_name":"Berrak \u015ei\u015fman","orcid":"https://orcid.org/0000-0001-8078-3305"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Berrak Sisman","raw_affiliation_strings":["The University of Texas at Dallas,Speech & Machine Learning (SML) Lab,USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Speech & Machine Learning (SML) Lab,USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100354178"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23183689,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"742","last_page":"749"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9896000027656555,"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/masking","display_name":"Masking (illustration)","score":0.792668342590332},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7169041037559509},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.6118606328964233},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4703866243362427},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06922432780265808}],"concepts":[{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.792668342590332},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7169041037559509},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.6118606328964233},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4703866243362427},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06922432780265808},{"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832297","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832297","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.75,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2021986246","https://openalex.org/W2057609679","https://openalex.org/W2396025094","https://openalex.org/W2471520273","https://openalex.org/W2603777577","https://openalex.org/W2890704021","https://openalex.org/W2902070858","https://openalex.org/W2962788625","https://openalex.org/W2972403660","https://openalex.org/W2972659941","https://openalex.org/W2997430147","https://openalex.org/W2998572311","https://openalex.org/W3008391559","https://openalex.org/W3015338123","https://openalex.org/W3016181583","https://openalex.org/W3095361818","https://openalex.org/W3096524539","https://openalex.org/W3098557217","https://openalex.org/W3100696337","https://openalex.org/W3162512456","https://openalex.org/W3163475957","https://openalex.org/W3197659778","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3210530853","https://openalex.org/W4224301045","https://openalex.org/W4286747238","https://openalex.org/W4366147765","https://openalex.org/W4372337821","https://openalex.org/W4375868953","https://openalex.org/W4375868976","https://openalex.org/W4385823264","https://openalex.org/W4392902857","https://openalex.org/W6762533536","https://openalex.org/W6772349387","https://openalex.org/W6772357204","https://openalex.org/W6779459370","https://openalex.org/W6805710207"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Voice":[0],"conversion":[1,129],"(VC)":[2],"aims":[3,90],"to":[4,91,102,118],"modify":[5],"the":[6,11,23,32,42,47,51,72,93,112],"speaker\u2019s":[7,24],"identity":[8,25],"while":[9],"preserving":[10],"linguistic":[12,27],"content.":[13],"Commonly,":[14],"VC":[15,122,133],"methods":[16,38],"use":[17],"an":[18],"encoder-decoder":[19,120],"architecture,":[20],"where":[21],"disentangling":[22],"from":[26],"information":[28],"is":[29,57,110,116],"crucial.":[30],"However,":[31],"disentanglement":[33,127],"approaches":[34],"used":[35],"in":[36,71,139,146],"these":[37],"are":[39],"limited":[40],"as":[41],"speaker":[43,75,97],"features":[44,98],"depend":[45],"on":[46],"phonetic":[48,94,104],"content":[49],"of":[50,96],"utterance,":[52],"compromising":[53],"disentanglement.":[54],"This":[55],"dependency":[56,95],"amplified":[58],"with":[59,85,142],"attention-based":[60,140],"methods.":[61],"To":[62],"address":[63],"this,":[64],"we":[65],"introduce":[66],"a":[67],"novel":[68],"masking":[69,77],"mechanism":[70],"input":[73,113],"before":[74],"encoding,":[76],"certain":[78],"discrete":[79],"speech":[80],"units":[81],"that":[82],"correspond":[83],"highly":[84],"phoneme":[86],"classes.":[87],"Our":[88,124],"work":[89],"reduce":[92],"by":[99],"restricting":[100],"access":[101],"some":[103],"information.":[105],"Furthermore,":[106],"since":[107],"our":[108],"approach":[109,125],"at":[111],"level,":[114],"it":[115],"applicable":[117],"any":[119],"based":[121],"framework.":[123],"improves":[126],"and":[128],"performance":[130],"across":[131],"multiple":[132],"methods,":[134],"showing":[135],"significant":[136],"effectiveness,":[137],"particularly":[138],"method,":[141],"44%":[143],"relative":[144],"improvement":[145],"objective":[147],"intelligibility.":[148]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}