{"id":"https://openalex.org/W4403656700","doi":"https://doi.org/10.1007/s10772-024-10161-1","title":"Generative adversarial networks for whispered to voiced speech conversion: a comparative study","display_name":"Generative adversarial networks for whispered to voiced speech conversion: a comparative study","publication_year":2024,"publication_date":"2024-10-22","ids":{"openalex":"https://openalex.org/W4403656700","doi":"https://doi.org/10.1007/s10772-024-10161-1"},"language":"en","primary_location":{"id":"doi:10.1007/s10772-024-10161-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10772-024-10161-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10772-024-10161-1.pdf","source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Speech Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10772-024-10161-1.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080633663","display_name":"Dominik Wagner","orcid":"https://orcid.org/0009-0006-7293-9131"},"institutions":[{"id":"https://openalex.org/I4210100612","display_name":"Georg Simon Ohm University of Applied Sciences Nuremberg","ror":"https://ror.org/00nggaz43","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210100612"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Dominik Wagner","raw_affiliation_strings":["Department of Computer Science , Technische Hochschule N\u00fcrnberg Georg Simon Ohm, Ke\u00dflerpl. 12, 90489, Nuremberg, Bavaria, Germany"],"raw_orcid":"https://orcid.org/0009-0006-7293-9131","affiliations":[{"raw_affiliation_string":"Department of Computer Science , Technische Hochschule N\u00fcrnberg Georg Simon Ohm, Ke\u00dflerpl. 12, 90489, Nuremberg, Bavaria, Germany","institution_ids":["https://openalex.org/I4210100612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047469130","display_name":"Ilja Baumann","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100612","display_name":"Georg Simon Ohm University of Applied Sciences Nuremberg","ror":"https://ror.org/00nggaz43","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210100612"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ilja Baumann","raw_affiliation_strings":["Department of Computer Science , Technische Hochschule N\u00fcrnberg Georg Simon Ohm, Ke\u00dflerpl. 12, 90489, Nuremberg, Bavaria, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Technische Hochschule N\u00fcrnberg Georg Simon Ohm, Ke\u00dflerpl. 12, 90489, Nuremberg, Bavaria, Germany","institution_ids":["https://openalex.org/I4210100612"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033302750","display_name":"Tobias Bocklet","orcid":"https://orcid.org/0009-0008-7780-8821"},"institutions":[{"id":"https://openalex.org/I4210100612","display_name":"Georg Simon Ohm University of Applied Sciences Nuremberg","ror":"https://ror.org/00nggaz43","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210100612"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias Bocklet","raw_affiliation_strings":["Department of Computer Science , Technische Hochschule N\u00fcrnberg Georg Simon Ohm, Ke\u00dflerpl. 12, 90489, Nuremberg, Bavaria, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Technische Hochschule N\u00fcrnberg Georg Simon Ohm, Ke\u00dflerpl. 12, 90489, Nuremberg, Bavaria, Germany","institution_ids":["https://openalex.org/I4210100612"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5080633663"],"corresponding_institution_ids":["https://openalex.org/I4210100612"],"apc_list":{"value":2780,"currency":"USD","value_usd":2780},"apc_paid":{"value":2780,"currency":"USD","value_usd":2780},"fwci":1.2902,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80198832,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"27","issue":"4","first_page":"1093","last_page":"1110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9907000064849854,"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":0.9148383736610413},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7756683826446533},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.717969536781311},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6631429195404053},{"id":"https://openalex.org/keywords/generative-adversarial-network","display_name":"Generative adversarial network","score":0.444196492433548},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42287677526474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3981660008430481},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.1044648289680481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9148383736610413},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7756683826446533},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.717969536781311},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6631429195404053},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.444196492433548},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42287677526474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3981660008430481},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.1044648289680481}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10772-024-10161-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10772-024-10161-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10772-024-10161-1.pdf","source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Speech Technology","raw_type":"journal-article"},{"id":"pmh:oai:kobv.de-opus4-th-nuernberg:4145","is_oa":false,"landing_page_url":"https://opus4.kobv.de/opus4-ohm/frontdoor/index/index/docId/4145","pdf_url":null,"source":{"id":"https://openalex.org/S4306401730","display_name":"OHMdok (Technische Hochschule N\u00fcrnberg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210100612","host_organization_name":"Georg Simon Ohm University of Applied Sciences Nuremberg","host_organization_lineage":["https://openalex.org/I4210100612"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s10772-024-10161-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10772-024-10161-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10772-024-10161-1.pdf","source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Speech Technology","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403656700.pdf","grobid_xml":"https://content.openalex.org/works/W4403656700.grobid-xml"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W1538607601","https://openalex.org/W1540787848","https://openalex.org/W1963637322","https://openalex.org/W1998648683","https://openalex.org/W2052246103","https://openalex.org/W2086300622","https://openalex.org/W2120605154","https://openalex.org/W2141998673","https://openalex.org/W2144404214","https://openalex.org/W2284050935","https://openalex.org/W2302255633","https://openalex.org/W2400434184","https://openalex.org/W2471520273","https://openalex.org/W2473388484","https://openalex.org/W2593414223","https://openalex.org/W2726515241","https://openalex.org/W2745644908","https://openalex.org/W2747874407","https://openalex.org/W2752782242","https://openalex.org/W2752796333","https://openalex.org/W2807627734","https://openalex.org/W2889417860","https://openalex.org/W2928165649","https://openalex.org/W2962795274","https://openalex.org/W2962866891","https://openalex.org/W2963035245","https://openalex.org/W2963300588","https://openalex.org/W2963341071","https://openalex.org/W2972471621","https://openalex.org/W2972597685","https://openalex.org/W2972986317","https://openalex.org/W2975414524","https://openalex.org/W2987496713","https://openalex.org/W2999905431","https://openalex.org/W3015338123","https://openalex.org/W3015465870","https://openalex.org/W3024869864","https://openalex.org/W3025844872","https://openalex.org/W3087665158","https://openalex.org/W3092028330","https://openalex.org/W3096918678","https://openalex.org/W3097538987","https://openalex.org/W3114227432","https://openalex.org/W3139878283","https://openalex.org/W3140957872","https://openalex.org/W3144035034","https://openalex.org/W3161172673","https://openalex.org/W3161558238","https://openalex.org/W3197273793","https://openalex.org/W3198270377","https://openalex.org/W3206916870","https://openalex.org/W3208900277","https://openalex.org/W3209059054","https://openalex.org/W4253928870","https://openalex.org/W4285077312","https://openalex.org/W4297841603","https://openalex.org/W4318752101","https://openalex.org/W4323322934","https://openalex.org/W6631190155","https://openalex.org/W6748409065","https://openalex.org/W6757817989","https://openalex.org/W6778823374","https://openalex.org/W7008777630"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2888032422","https://openalex.org/W2996316059","https://openalex.org/W4385421777","https://openalex.org/W4377980832","https://openalex.org/W2897769091","https://openalex.org/W2845413374","https://openalex.org/W3005996785","https://openalex.org/W4297411772","https://openalex.org/W4235873501"],"abstract_inverted_index":{"Abstract":[0],"Generative":[1],"Adversarial":[2],"Networks":[3],"(GANs)":[4],"have":[5],"demonstrated":[6],"promising":[7],"results":[8,97],"as":[9,135,137],"end-to-end":[10],"models":[11,34],"for":[12,32,58,76],"whispered":[13,60],"to":[14,35,42,46,52,61,189],"voiced":[15,37,62],"speech":[16,38,63,102],"conversion.":[17],"Leveraging":[18],"non-autoregressive":[19],"systems":[20],"like":[21],"GANs":[22],"capable":[23],"of":[24,80,160,169,187],"performing":[25],"conditional":[26],"waveform":[27],"generation":[28],"eliminates":[29],"the":[30,54,59,78,101,107,111,117,164],"need":[31],"separate":[33],"estimate":[36],"features,":[39],"and":[40,83,91,131,176,180],"leads":[41],"faster":[43],"inference":[44],"compared":[45],"autoregressive":[47],"methods.":[48],"This":[49],"study":[50],"aims":[51],"identify":[53],"optimal":[55],"GAN":[56],"architecture":[57,109],"conversion":[64,103],"task":[65],"by":[66,119,138],"comparing":[67],"six":[68],"state-of-the-art":[69],"models.":[70],"Furthermore,":[71,171],"we":[72],"present":[73],"a":[74,156,167],"method":[75],"evaluating":[77],"preservation":[79],"speaker":[81,178],"identity":[82,179],"local":[84],"accent,":[85,181],"using":[86,127,146],"embeddings":[87],"obtained":[88],"from":[89],"speaker-":[90],"language":[92,184],"identification":[93],"systems.":[94],"Our":[95],"experimental":[96],"show":[98],"that":[99],"building":[100],"system":[104],"based":[105],"on":[106],"HiFi-GAN":[108,154,172],"yields":[110],"best":[112],"objective":[113],"evaluation":[114],"scores,":[115],"outperforming":[116,163],"baseline":[118,165],"$$\\sim$$":[120,139,190],"<mml:math":[121,140,191],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\">":[122,141,192],"<mml:mo>\u223c</mml:mo>":[123,142,193],"</mml:math>":[124,143,194],"9%":[125],"relative":[126,145],"frequency-weighted":[128],"Signal-to-Noise":[129],"Ratio":[130],"Log":[132],"Likelihood":[133],"Ratio,":[134],"well":[136],"29%":[144],"Root":[147],"Mean":[148],"Squared":[149],"Error.":[150],"In":[151],"subjective":[152],"tests,":[153],"yielded":[155],"mean":[157],"opinion":[158],"score":[159,168],"2.9,":[161],"significantly":[162],"with":[166,182],"1.4.":[170],"enhanced":[173],"ASR":[174],"performance":[175],"preserved":[177],"correct":[183],"detection":[185],"rates":[186],"up":[188],"98%.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}