{"id":"https://openalex.org/W4206789583","doi":"https://doi.org/10.23919/eusipco54536.2021.9616228","title":"Data Augmentation Using CycleGAN for End-to-End Children ASR","display_name":"Data Augmentation Using CycleGAN for End-to-End Children ASR","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W4206789583","doi":"https://doi.org/10.23919/eusipco54536.2021.9616228"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616228","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616228","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":["Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar, Gujarat, India"],"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar, Gujarat, India","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 P. Amin","raw_affiliation_strings":["Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar, Gujarat, India"],"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar, Gujarat, India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030912143","display_name":"Hardik B. Sailor","orcid":"https://orcid.org/0000-0001-6872-5153"},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hardik B. Sailor","raw_affiliation_strings":["Samsung R&D Institute, India"],"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute, India","institution_ids":["https://openalex.org/I4210139030"]}]},{"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 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":["Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar, Gujarat, India"],"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar, Gujarat, India","institution_ids":["https://openalex.org/I98389781"]}]}],"institutions":[],"countries_distinct_count":1,"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":1.6501,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.87422604,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"511","last_page":"515"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9993000030517578,"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":0.9980000257492065,"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":0.7075521349906921},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6879678964614868},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6505632996559143},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.610450029373169},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5815655589103699},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5046480894088745},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.48723283410072327},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4713194966316223},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41869133710861206},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3416927456855774},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13358229398727417},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.05523446202278137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7075521349906921},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6879678964614868},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6505632996559143},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.610450029373169},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5815655589103699},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5046480894088745},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.48723283410072327},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4713194966316223},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41869133710861206},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3416927456855774},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13358229398727417},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.05523446202278137},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C505870484","wikidata":"https://www.wikidata.org/wiki/Q180538","display_name":"Fishery","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616228","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616228","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2067063915","https://openalex.org/W2094954292","https://openalex.org/W2100118853","https://openalex.org/W2102113734","https://openalex.org/W2115002762","https://openalex.org/W2402172738","https://openalex.org/W2407080277","https://openalex.org/W2471520273","https://openalex.org/W2577946330","https://openalex.org/W2753797950","https://openalex.org/W2774848319","https://openalex.org/W2803039862","https://openalex.org/W2803431233","https://openalex.org/W2883586237","https://openalex.org/W2936774411","https://openalex.org/W2937579788","https://openalex.org/W2962780374","https://openalex.org/W2962793481","https://openalex.org/W2963073614","https://openalex.org/W2972818416","https://openalex.org/W2972841547","https://openalex.org/W3007328579","https://openalex.org/W3008739861","https://openalex.org/W3015927303","https://openalex.org/W3019581400","https://openalex.org/W3094704668","https://openalex.org/W3094833745","https://openalex.org/W3095936335","https://openalex.org/W3097017391","https://openalex.org/W3106470464","https://openalex.org/W6675365184","https://openalex.org/W6712586537","https://openalex.org/W6713762819","https://openalex.org/W6768035920","https://openalex.org/W6784552839"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2151749779","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2101155126","https://openalex.org/W4404782863"],"abstract_inverted_index":{"Recent":[0],"deep":[1,41],"learning":[2],"algorithms":[3],"are":[4],"known":[5],"to":[6,22,31,38,106,131],"perform":[7],"better":[8],"for":[9,53],"Automatic":[10],"Speech":[11],"Recognition":[12],"(ASR)":[13],"of":[14,34,48,91,102,114,127],"adult":[15,93,121],"speakers,":[16],"however,":[17],"yet":[18],"remains":[19],"a":[20],"challenge":[21],"recognize":[23],"children's":[24,35],"speech":[25,36,94,122],"with":[26,70,99],"the":[27,40,49,100,107,112,124],"similar":[28],"accuracy.":[29],"Due":[30],"less":[32],"availability":[33],"data":[37,44,61,73],"train":[39],"neural":[42],"network,":[43],"augmentation":[45,62,74],"is":[46,65,75],"one":[47],"key":[50],"research":[51],"areas":[52],"children":[54],"ASR.":[55],"In":[56,85,110],"this":[57],"paper,":[58],"voice":[59],"conversion-based":[60],"using":[63,81],"CycleGAN":[64,119],"explored":[66],"and":[67,71,118],"performance":[68,97],"comparison":[69],"without":[72],"presented.":[76],"ASR":[77],"experiments":[78],"were":[79],"performed":[80],"TLT":[82],"school":[83],"corpus.":[84],"our":[86],"experiment,":[87],"CycleGAN-based":[88],"200":[89],"hours":[90],"converted":[92,120],"showed":[95,123],"good":[96],"improvement":[98],"reduction":[101,126],"5.58%":[103],"WER":[104,129],"compared":[105,130],"baseline":[108,132],"system.":[109],"addition,":[111],"combination":[113],"SpecAugment,":[115],"speed":[116],"perturbed,":[117],"highest":[125],"7.44%":[128],"system":[133],"<sup":[134],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[135],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[136],".":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-22T08:09:32.410652","created_date":"2025-10-10T00:00:00"}