{"id":"https://openalex.org/W4391305764","doi":"https://doi.org/10.1109/taslp.2024.3359352","title":"Disentanglement in a GAN for Unconditional Speech Synthesis","display_name":"Disentanglement in a GAN for Unconditional Speech Synthesis","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391305764","doi":"https://doi.org/10.1109/taslp.2024.3359352"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3359352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3359352","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5085677838","display_name":"Matthew Baas","orcid":"https://orcid.org/0000-0003-3001-6292"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":true,"raw_author_name":"Matthew Baas","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Stellenbosch University, Stellenbosch, South Africa"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Stellenbosch University, Stellenbosch, South Africa","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040305929","display_name":"Herman Kamper","orcid":"https://orcid.org/0000-0003-2980-3475"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Herman Kamper","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Stellenbosch University, Stellenbosch, South Africa"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Stellenbosch University, Stellenbosch, South Africa","institution_ids":["https://openalex.org/I26092322"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5085677838"],"corresponding_institution_ids":["https://openalex.org/I26092322"],"apc_list":null,"apc_paid":null,"fwci":2.9096,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.91349927,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"32","issue":null,"first_page":"1324","last_page":"1335"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.992900013923645,"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":0.992900013923645,"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":0.9449999928474426,"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/computer-science","display_name":"Computer science","score":0.3684343099594116},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3587380051612854},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34094512462615967}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3684343099594116},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3587380051612854},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34094512462615967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3359352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3359352","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W2014555931","https://openalex.org/W2067295501","https://openalex.org/W2103869314","https://openalex.org/W2519091744","https://openalex.org/W2549139847","https://openalex.org/W2623550831","https://openalex.org/W2797583228","https://openalex.org/W2933138175","https://openalex.org/W2962770929","https://openalex.org/W2962788625","https://openalex.org/W3031894486","https://openalex.org/W3035187956","https://openalex.org/W3095488131","https://openalex.org/W3106255532","https://openalex.org/W3140429000","https://openalex.org/W3147966746","https://openalex.org/W3162850270","https://openalex.org/W3173102319","https://openalex.org/W3174807077","https://openalex.org/W3197580070","https://openalex.org/W3198217962","https://openalex.org/W3209059054","https://openalex.org/W3210530853","https://openalex.org/W4224035735","https://openalex.org/W4225309689","https://openalex.org/W4296068974","https://openalex.org/W4319862675","https://openalex.org/W4368304415","https://openalex.org/W4385535562","https://openalex.org/W4385571190","https://openalex.org/W4386071957","https://openalex.org/W6631190155","https://openalex.org/W6679045638","https://openalex.org/W6718379498","https://openalex.org/W6743994364","https://openalex.org/W6745560452","https://openalex.org/W6749927861","https://openalex.org/W6750665317","https://openalex.org/W6755257315","https://openalex.org/W6762533536","https://openalex.org/W6765779288","https://openalex.org/W6779093361","https://openalex.org/W6780179280","https://openalex.org/W6783182287","https://openalex.org/W6783867762","https://openalex.org/W6790356757","https://openalex.org/W6790978476","https://openalex.org/W6809885388","https://openalex.org/W6810325043","https://openalex.org/W6838639034","https://openalex.org/W6839243001","https://openalex.org/W6849109464"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655","https://openalex.org/W2359140296"],"abstract_inverted_index":{"Can":[0],"we":[1,42,103,160,180],"develop":[2],"a":[3,12,47,58,76,85,105,111],"model":[4],"that":[5,91,154,196,209],"can":[6,169,213],"synthesize":[7],"realistic":[8],"speech":[9,53,140,186,205],"directly":[10],"from":[11],"latent":[13,60,78,156,211],"space,":[14],"without":[15],"explicit":[16],"conditioning?":[17],"Despite":[18],"several":[19,174],"efforts":[20],"over":[21],"the":[22,64,126,167,203],"last":[23],"decade,":[24],"previous":[25],"adversarial":[26,49],"and":[27,190,208],"diffusion-based":[28],"approaches":[29],"still":[30,199],"struggle":[31],"to":[32,56,75,84,113,172,216,219],"achieve":[33],"this,":[34,41],"even":[35],"on":[36,125],"small-vocabulary":[37,127],"datasets.":[38],"To":[39,99],"address":[40],"propose":[43],"AudioStyleGAN":[44],"(ASGAN)":[45],"\u2013":[46],"generative":[48],"network":[50],"for":[51],"unconditional":[52,139,204],"synthesis":[54,69,206],"tailored":[55],"learn":[57],"disentangled":[59,77,210],"space.":[61],"Building":[62],"upon":[63],"StyleGAN":[65],"family":[66],"of":[67,87,107],"image":[68],"models,":[70,223],"ASGAN":[71],"maps":[72],"sampled":[73],"noise":[74],"vector":[79],"which":[80,117],"is":[81,94,143,158],"then":[82],"mapped":[83],"sequence":[86],"audio":[88],"features":[89],"so":[90],"signal":[92],"aliasing":[93],"suppressed":[95],"at":[96],"every":[97],"layer.":[98],"successfully":[100],"train":[101],"ASGAN,":[102],"introduce":[104],"number":[106],"new":[108],"techniques,":[109],"including":[110],"modification":[112],"adaptive":[114],"discriminator":[115,120],"augmentation":[116],"probabilistically":[118],"skips":[119],"updates.":[121],"We":[122,152],"apply":[123],"it":[124,134],"Google":[128],"Speech":[129],"Commands":[130],"digits":[131],"dataset,":[132],"where":[133],"achieves":[135],"state-of-the-art":[136],"results":[137],"in":[138,166,183,202],"synthesis.":[141],"It":[142],"also":[144],"substantially":[145],"faster":[146],"than":[147],"existing":[148],"top-performing":[149],"diffusion":[150],"models.":[151],"confirm":[153],"ASGAN's":[155],"space":[157,168],"disentangled:":[159],"demonstrate":[161],"how":[162],"simple":[163],"linear":[164],"operations":[165],"be":[170,214],"used":[171,215],"perform":[173,181],"tasks":[175],"unseen":[176,220],"during":[177],"training.":[178],"Specifically,":[179],"evaluations":[182],"voice":[184],"conversion,":[185],"enhancement,":[187],"speaker":[188],"verification,":[189],"keyword":[191],"classification.":[192],"Our":[193],"work":[194],"indicates":[195],"GANs":[197],"are":[198],"highly":[200],"competitive":[201],"landscape,":[207],"spaces":[212],"aid":[217],"generalization":[218],"tasks.":[221],"Code,":[222],"samples:":[224],"<uri":[225],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[226],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/RF5/simple-asgan/</uri>":[227],".":[228]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}