{"id":"https://openalex.org/W2987496713","doi":"https://doi.org/10.23919/eusipco.2019.8902961","title":"Effectiveness of Cross-Domain Architectures for Whisper-to-Normal Speech Conversion","display_name":"Effectiveness of Cross-Domain Architectures for Whisper-to-Normal Speech Conversion","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2987496713","doi":"https://doi.org/10.23919/eusipco.2019.8902961","mag":"2987496713"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco.2019.8902961","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2019.8902961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 27th European Signal Processing Conference (EUSIPCO)","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/A5063582658","display_name":"Mihir Parmar","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mihir Parmar","raw_affiliation_strings":["Speech Research Lab, DA-IICT, Gandhinagar, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Research Lab, DA-IICT, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062542902","display_name":"Savan Doshi","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Savan Doshi","raw_affiliation_strings":["Speech Research Lab, DA-IICT, Gandhinagar, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Research Lab, DA-IICT, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091143209","display_name":"Nirmesh J. Shah","orcid":"https://orcid.org/0000-0002-7294-6757"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nirmesh J. Shah","raw_affiliation_strings":["Speech Research Lab, DA-IICT, Gandhinagar, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Research Lab, DA-IICT, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018555559","display_name":"Maitreya Patel","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Maitreya Patel","raw_affiliation_strings":["Speech Research Lab, DA-IICT, Gandhinagar, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Research Lab, DA-IICT, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043002276","display_name":"Hemant A. Patil","orcid":"https://orcid.org/0000-0002-4068-2005"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemant A. Patil","raw_affiliation_strings":["Speech Research Lab, DA-IICT, Gandhinagar, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Research Lab, DA-IICT, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98389781"],"apc_list":null,"apc_paid":null,"fwci":1.7204,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.85246528,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976999759674072,"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":0.991599977016449,"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":0.7483437061309814},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6520384550094604},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6330527663230896},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5959468483924866},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5224996209144592},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.484408438205719},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.43487703800201416},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3937535285949707},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3670274317264557},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16769689321517944}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7483437061309814},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6520384550094604},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6330527663230896},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5959468483924866},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5224996209144592},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.484408438205719},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.43487703800201416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3937535285949707},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3670274317264557},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16769689321517944},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco.2019.8902961","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2019.8902961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 27th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W9125697","https://openalex.org/W96541173","https://openalex.org/W188951208","https://openalex.org/W1187407439","https://openalex.org/W1522301498","https://openalex.org/W1557133539","https://openalex.org/W2006033171","https://openalex.org/W2022045190","https://openalex.org/W2022047569","https://openalex.org/W2023850592","https://openalex.org/W2042204480","https://openalex.org/W2046033161","https://openalex.org/W2056852181","https://openalex.org/W2071431631","https://openalex.org/W2095026407","https://openalex.org/W2105677113","https://openalex.org/W2107221565","https://openalex.org/W2119648481","https://openalex.org/W2120605154","https://openalex.org/W2142691710","https://openalex.org/W2163833513","https://openalex.org/W2295406225","https://openalex.org/W2395552930","https://openalex.org/W2400434184","https://openalex.org/W2473289087","https://openalex.org/W2526493173","https://openalex.org/W2583038182","https://openalex.org/W2593414223","https://openalex.org/W2598581049","https://openalex.org/W2639888510","https://openalex.org/W2746457594","https://openalex.org/W2747744257","https://openalex.org/W2765811365","https://openalex.org/W2787748320","https://openalex.org/W2802304149","https://openalex.org/W2888796252","https://openalex.org/W2889417860","https://openalex.org/W2935803161","https://openalex.org/W2938537202","https://openalex.org/W2951939904","https://openalex.org/W2962793481","https://openalex.org/W2962896155","https://openalex.org/W2963971656","https://openalex.org/W2964121744","https://openalex.org/W3132518930","https://openalex.org/W3137116880","https://openalex.org/W4234890202","https://openalex.org/W4245838404","https://openalex.org/W4302589540","https://openalex.org/W6631190155","https://openalex.org/W6633482676","https://openalex.org/W6711678763","https://openalex.org/W6712874156","https://openalex.org/W6735204497","https://openalex.org/W6742802039","https://openalex.org/W6751445809","https://openalex.org/W6790633789","https://openalex.org/W7008777630"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W4246396837","https://openalex.org/W2482350142","https://openalex.org/W3176240006","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4288019534","https://openalex.org/W4310988119"],"abstract_inverted_index":{"Though":[0],"whisper":[1],"is":[2,11,62],"a":[3,127],"typical":[4],"way":[5],"of":[6,90],"natural":[7],"speech":[8,15,18,41,131],"communication,":[9],"it":[10],"different":[12],"from":[13,133],"normal":[14,130],"w.r.t.":[16],"to":[17,34,82,112],"production":[19],"and":[20,54,85],"perception":[21],"perspective.":[22],"Recently,":[23],"authors":[24],"have":[25,103],"proposed":[26,64,74,100,124],"Generative":[27],"Adversarial":[28,59],"Network":[29,60],"(GAN)-based":[30],"architecture":[31],"(namely,":[32],"DiscoGAN)":[33],"discover":[35],"such":[36],"cross-domain":[37,67,101],"relationships":[38],"for":[39,65],"whisper-to-normal":[40],"(WHSP2SPCH)":[42],"conversion.":[43,69],"In":[44,56],"this":[45,49],"paper,":[46],"we":[47,96],"extend":[48],"study":[50],"with":[51],"detailed":[52],"theory":[53],"analysis.":[55],"addition,":[57],"Cycle-consistent":[58],"(CycleGAN)":[61],"also":[63],"the":[66,73,83,99,113,117,123],"WHSP2SPCH":[68],"We":[70],"observe":[71,97],"that":[72,79,98,122],"systems":[75],"yield":[76],"objective":[77],"results":[78],"are":[80,86],"comparable":[81],"baseline,":[84],"superior":[87],"in":[88,116],"terms":[89],"fundamental":[91],"frequency":[92],"(i.e.,F0)":[93],"prediction.":[94],"Moreover,":[95],"architectures":[102],"been":[104],"preferred":[105],"55.75%":[106],"(on":[107],"average)":[108],"times":[109],"more":[110,128],"compared":[111],"traditional":[114],"GAN":[115],"subjective":[118],"evaluations.":[119],"This":[120],"reveals":[121],"method":[125],"yields":[126],"natural-sounding":[129],"converted":[132],"whispered":[134],"speech.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}