{"id":"https://openalex.org/W4401752854","doi":"https://doi.org/10.1109/spcom60851.2024.10631628","title":"Voice Conversion Based Data Augmentation Using CycleGAN for Children's ASR","display_name":"Voice Conversion Based Data Augmentation Using CycleGAN for Children's ASR","publication_year":2024,"publication_date":"2024-07-01","ids":{"openalex":"https://openalex.org/W4401752854","doi":"https://doi.org/10.1109/spcom60851.2024.10631628"},"language":"en","primary_location":{"id":"doi:10.1109/spcom60851.2024.10631628","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/spcom60851.2024.10631628","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Signal Processing and Communications (SPCOM)","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/A5006494479","display_name":"Dipesh K. Singh","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani Institute of Information and Communication Technology","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Dipesh K. Singh","raw_affiliation_strings":["DAIICT,Gujarat,India,382007"],"affiliations":[{"raw_affiliation_string":"DAIICT,Gujarat,India,382007","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056800832","display_name":"Preet P. Amin","orcid":"https://orcid.org/0000-0001-7944-8614"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani Institute of Information and Communication Technology","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Preet Amin","raw_affiliation_strings":["DAIICT,Gujarat,India,382007"],"affiliations":[{"raw_affiliation_string":"DAIICT,Gujarat,India,382007","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","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 Institute of Information and Communication Technology","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":["DAIICT,Gujarat,India,382007"],"affiliations":[{"raw_affiliation_string":"DAIICT,Gujarat,India,382007","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030912143","display_name":"Hardik B. Sailor","orcid":"https://orcid.org/0000-0001-6872-5153"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hardik B. Sailor","raw_affiliation_strings":["Institute for Infocomm Research (I2R) A*STAR,Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R) A*STAR,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5006494479"],"corresponding_institution_ids":["https://openalex.org/I98389781"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11418916,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/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"}},"topics":[{"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/T12031","display_name":"Speech and dialogue systems","score":0.9970999956130981,"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":0.9962000250816345,"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":0.6503809690475464},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6049688458442688},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.328707218170166}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6503809690475464},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6049688458442688},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.328707218170166}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/spcom60851.2024.10631628","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/spcom60851.2024.10631628","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Signal Processing and Communications (SPCOM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W25255646","https://openalex.org/W104463061","https://openalex.org/W144209617","https://openalex.org/W1994888226","https://openalex.org/W2100118853","https://openalex.org/W2471520273","https://openalex.org/W2577946330","https://openalex.org/W2587488139","https://openalex.org/W2937579788","https://openalex.org/W3007928779","https://openalex.org/W3160666406","https://openalex.org/W3196589454","https://openalex.org/W3202786883","https://openalex.org/W4200560037","https://openalex.org/W4206789583","https://openalex.org/W6732248266"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"Extensive":[0],"use":[1],"of":[2,16,53,64,118,143],"voice":[3,88,115],"assistants":[4],"by":[5],"children":[6,54],"in":[7,27,105,147,167],"their":[8],"day-to-day":[9],"life":[10],"activities":[11],"demand":[12],"for":[13,21,31,75,102,113,169],"better":[14,30],"performance":[15,63],"Automatic":[17],"Speech":[18],"Recognition":[19],"(ASR)":[20],"children's":[22,65,76],"speech.":[23,33],"The":[24],"recent":[25],"advancements":[26],"ASR":[28,74,121,168],"perform":[29],"adult":[32],"However,":[34],"due":[35],"to":[36,60,150],"acoustic":[37],"mismatch":[38],"(in":[39],"particular,":[40],"higher":[41],"<tex":[42],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[43],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$F_{0}$</tex>":[44],"and":[45,50,120,145,157],"thus,":[46],"poor":[47],"spectral":[48],"resolution,":[49],"less":[51],"availability":[52],"data),":[55],"it":[56],"remains":[57],"a":[58,70,94,140],"challenge":[59],"improve":[61],"the":[62,87,106,126,131,151,155],"ASR.":[66],"In":[67,84,133],"this":[68,85],"context,":[69],"shared":[71],"task":[72],"on":[73,125,154],"speech":[77,127],"2021":[78],"was":[79],"organized":[80],"during":[81,130],"INTERSPEECH":[82],"2021.":[83],"paper,":[86],"conversion-based":[89],"data":[90,128,137],"augmentation":[91,138],"technique":[92],"using":[93],"cycle-consistent":[95],"generative":[96],"adversarial":[97],"network":[98],"(CycleGAN)":[99],"is":[100,111,180],"investigated":[101],"closed":[103],"track":[104],"challenge.":[107,132],"Here,":[108],"CycleGAN":[109,119],"training":[110],"exploited":[112],"children-to-children":[114],"conversion.":[116],"Training":[117],"experiments":[122],"are":[123],"performed":[124],"provided":[129],"our":[134],"experiments,":[135],"CycleGAN-based":[136],"showed":[139],"relative":[141],"improvement":[142],"9%":[144],"3%":[146],"WER":[148],"compared":[149],"baseline":[152],"system":[153],"Dev":[156],"Eval":[158],"sets,":[159],"respectively.":[160],"This":[161],"work":[162],"may":[163],"find":[164],"its":[165],"significance":[166],"low":[170],"resource":[171],"languages,":[172],"where":[173],"Librispeech":[174],"or":[175],"any":[176],"other":[177],"external":[178],"dataset":[179],"not":[181],"an":[182],"option.":[183]},"counts_by_year":[],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}