{"id":"https://openalex.org/W3114227432","doi":"https://doi.org/10.23919/eusipco47968.2020.9287385","title":"CinC-GAN for Effective F<sub>0</sub>prediction for Whisper-to-Normal Speech Conversion","display_name":"CinC-GAN for Effective F<sub>0</sub>prediction for Whisper-to-Normal Speech Conversion","publication_year":2020,"publication_date":"2020-12-18","ids":{"openalex":"https://openalex.org/W3114227432","doi":"https://doi.org/10.23919/eusipco47968.2020.9287385","mag":"3114227432"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco47968.2020.9287385","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th 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/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, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Research Lab, DA-IICT, India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091764885","display_name":"Mirali Purohit","orcid":"https://orcid.org/0009-0009-0354-4920"},"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":"Mirali Purohit","raw_affiliation_strings":["Speech Research Lab, DA-IICT, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Research Lab, DA-IICT, India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109455358","display_name":"Jui Shah","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":"Jui Shah","raw_affiliation_strings":["Speech Research Lab, DA-IICT, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Research Lab, DA-IICT, 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, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Research Lab, DA-IICT, 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":0.46,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.66623289,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"411","last_page":"415"},"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":0.998199999332428,"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":0.6261464953422546},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5542049407958984},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5366240739822388},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45124906301498413},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.43830054998397827},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06748461723327637}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6261464953422546},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5542049407958984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5366240739822388},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45124906301498413},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43830054998397827},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06748461723327637}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco47968.2020.9287385","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W96541173","https://openalex.org/W1187407439","https://openalex.org/W1557133539","https://openalex.org/W1959608418","https://openalex.org/W2022045190","https://openalex.org/W2023850592","https://openalex.org/W2042204480","https://openalex.org/W2056852181","https://openalex.org/W2071431631","https://openalex.org/W2086796102","https://openalex.org/W2105677113","https://openalex.org/W2120605154","https://openalex.org/W2142691710","https://openalex.org/W2156142001","https://openalex.org/W2163833513","https://openalex.org/W2295406225","https://openalex.org/W2400434184","https://openalex.org/W2473289087","https://openalex.org/W2639888510","https://openalex.org/W2889417860","https://openalex.org/W2902070858","https://openalex.org/W2937579788","https://openalex.org/W2962793481","https://openalex.org/W2962903125","https://openalex.org/W2972986317","https://openalex.org/W2987496713","https://openalex.org/W3012437242","https://openalex.org/W3015465870","https://openalex.org/W3137116880","https://openalex.org/W4234890202","https://openalex.org/W4302589540","https://openalex.org/W6600355423","https://openalex.org/W6640963894","https://openalex.org/W6712874156","https://openalex.org/W7008777630"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2051487156","https://openalex.org/W2073681303","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"],"abstract_inverted_index":{"Recently,":[0,34],"Generative":[1,41],"Adversarial":[2,42],"Networks":[3,43],"(GAN)based":[4],"methods":[5],"have":[6,36],"shown":[7],"remarkable":[8],"performance":[9],"for":[10,45,56,64,149],"the":[11,21,28,71,102,108,115,139,145,153,156],"Voice":[12],"Conversion":[13],"and":[14,62,122,126,131,147,152],"WHiSPer-to-normal":[15],"SPeeCH":[16],"(WHSP2SPCH)":[17],"conversion.":[18,47],"One":[19],"of":[20,30,74,110,159],"key":[22],"challenges":[23],"in":[24,83,104],"WHSP2SPCH":[25,46],"conversion":[26],"is":[27,97],"prediction":[29],"fundamental":[31],"frequency":[32],"(F0).":[33],"authors":[35],"proposed":[37,116],"state-of-the-art":[38],"method":[39,50,117],"Cycle-Consistent":[40],"(CycleGAN)":[44],"The":[48,129],"CycleGAN-based":[49],"uses":[51],"two":[52],"different":[53],"models,":[54],"one":[55],"Mel":[57],"Cepstral":[58],"Coefficients":[59],"(MCC)":[60],"mapping,":[61],"another":[63],"F0prediction,":[65],"where":[66],"F0is":[67],"highly":[68],"dependent":[69],"on":[70,118,124],"pre-trained":[72],"model":[73],"MCC":[75,111],"mapping.":[76,112],"This":[77],"leads":[78],"to":[79,100],"additional":[80],"nonlinear":[81],"noise":[82],"predicted":[84],"F0.":[85],"To":[86],"suppress":[87],"this":[88],"noise,":[89],"we":[90,143],"propose":[91],"Cycle-in-Cycle":[92],"GAN":[93],"(i.e.,":[94],"CinC-GAN).":[95],"It":[96],"specially":[98],"designed":[99],"increase":[101],"effectiveness":[103],"F0prediction":[105],"without":[106],"losing":[107],"accuracy":[109],"We":[113],"evaluated":[114],"a":[119],"non-parallel":[120],"setting":[121],"analyzed":[123],"speaker-specific,":[125],"gender-specific":[127],"tasks.":[128],"objective":[130],"subjective":[132],"tests":[133],"show":[134,155],"that":[135],"CinC-GAN":[136,148],"significantly":[137],"outperforms":[138],"CycleGAN.":[140],"In":[141],"addition,":[142],"analyze":[144],"CycleGAN":[146],"unseen":[150],"speakers":[151],"results":[154],"clear":[157],"superiority":[158],"CinC-GAN.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}