{"id":"https://openalex.org/W3016258016","doi":"https://doi.org/10.1109/icassp40776.2020.9053891","title":"In-Domain and Out-of-Domain Data Augmentation to Improve Children\u2019s Speaker Verification System in Limited Data Scenario","display_name":"In-Domain and Out-of-Domain Data Augmentation to Improve Children\u2019s Speaker Verification System in Limited Data Scenario","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016258016","doi":"https://doi.org/10.1109/icassp40776.2020.9053891","mag":"3016258016"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053891","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5063682063","display_name":"S. Shahnawazuddin","orcid":"https://orcid.org/0000-0002-3916-9693"},"institutions":[{"id":"https://openalex.org/I11793825","display_name":"National Institute of Technology Patna","ror":"https://ror.org/056wyhh33","country_code":"IN","type":"education","lineage":["https://openalex.org/I11793825","https://openalex.org/I4210152752"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"S. Shahnawazuddin","raw_affiliation_strings":["Department of Electronics and Communication Engineering, NIT Patna, India"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Communication Engineering, NIT Patna, India","institution_ids":["https://openalex.org/I11793825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070407855","display_name":"Waquar Ahmad","orcid":"https://orcid.org/0000-0001-7817-3313"},"institutions":[{"id":"https://openalex.org/I114845381","display_name":"National Institute of Technology Calicut","ror":"https://ror.org/03yyd7552","country_code":"IN","type":"education","lineage":["https://openalex.org/I114845381"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Waquar Ahmad","raw_affiliation_strings":["Department of Electronics and Communication Engineering, NIT Calicut, India"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Communication Engineering, NIT Calicut, India","institution_ids":["https://openalex.org/I114845381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015353805","display_name":"Nagaraj Adiga","orcid":"https://orcid.org/0000-0002-3438-567X"},"institutions":[{"id":"https://openalex.org/I142617266","display_name":"University of Crete","ror":"https://ror.org/00dr28g20","country_code":"GR","type":"education","lineage":["https://openalex.org/I142617266"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Nagaraj Adiga","raw_affiliation_strings":["Department of Computer Science, University of Crete, Greece"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Crete, Greece","institution_ids":["https://openalex.org/I142617266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059592615","display_name":"Avinash Kumar","orcid":"https://orcid.org/0000-0001-7953-0247"},"institutions":[{"id":"https://openalex.org/I101326570","display_name":"National Institute of Technology Sikkim","ror":"https://ror.org/04pam3b03","country_code":"IN","type":"education","lineage":["https://openalex.org/I101326570"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Avinash Kumar","raw_affiliation_strings":["Department of Electronics and Communication Engineering, NIT Sikkim, India"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Communication Engineering, NIT Sikkim, India","institution_ids":["https://openalex.org/I101326570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5063682063"],"corresponding_institution_ids":["https://openalex.org/I11793825"],"apc_list":null,"apc_paid":null,"fwci":1.8558,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.88258003,"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":"7554","last_page":"7558"},"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":0.9973999857902527,"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":0.9904000163078308,"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":0.7230062484741211},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6475827693939209},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5231955051422119},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5221153497695923},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.4867589473724365},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4536605775356293},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44405901432037354},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.43941962718963623},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4313563406467438},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39385417103767395},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3586077094078064},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33701130747795105},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12011167407035828}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7230062484741211},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6475827693939209},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5231955051422119},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5221153497695923},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.4867589473724365},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4536605775356293},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44405901432037354},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.43941962718963623},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4313563406467438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39385417103767395},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3586077094078064},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33701130747795105},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12011167407035828},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053891","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"},{"score":0.4000000059604645,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W17704661","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1540779870","https://openalex.org/W1589137271","https://openalex.org/W1762484328","https://openalex.org/W2040105822","https://openalex.org/W2094954292","https://openalex.org/W2101261946","https://openalex.org/W2112844139","https://openalex.org/W2130722890","https://openalex.org/W2150769028","https://openalex.org/W2250357346","https://openalex.org/W2296496557","https://openalex.org/W2402172738","https://openalex.org/W2407080277","https://openalex.org/W2578415609","https://openalex.org/W2748488820","https://openalex.org/W2757257005","https://openalex.org/W2768739064","https://openalex.org/W2774848319","https://openalex.org/W2783782089","https://openalex.org/W2890964092","https://openalex.org/W2962732406","https://openalex.org/W6600719064","https://openalex.org/W6629717138","https://openalex.org/W6631362777","https://openalex.org/W6635152626","https://openalex.org/W6637956674","https://openalex.org/W6691509046","https://openalex.org/W6696962386","https://openalex.org/W6713762819","https://openalex.org/W6732217805","https://openalex.org/W6746801104"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W3141593045","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W2407001684","https://openalex.org/W3096066489","https://openalex.org/W3119184205"],"abstract_inverted_index":{"In":[0,140],"this":[1,47,129],"paper,":[2],"we":[3,27],"present":[4],"our":[5],"efforts":[6],"towards":[7],"developing":[8],"a":[9,135,176],"robust":[10],"automatic":[11],"speaker":[12],"verification":[13],"(ASV)":[14],"system":[15],"for":[16,58,66,122,150],"children":[17],"when":[18],"the":[19,30,73,85,99,152,164],"domain-specific":[20],"data":[21,36,42,62,70,118,158],"is":[22,78,91,119,148],"limited.":[23],"For":[24,68],"that":[25,111],"purpose,":[26],"have":[28],"studied":[29,45],"effect":[31],"of":[32,41,53,103,112,157],"in-domain":[33,61],"and":[34,50],"out-of-domain":[35,69],"augmentation.":[37,67,123],"Several":[38],"different":[39],"combinations":[40],"augmentation":[43,159],"are":[44,56,160],"in":[46,128],"work.":[48],"Speed":[49],"pitch":[51],"perturbation":[52],"children's":[54,82,113],"speech":[55,77,96,105],"employed":[57],"synthetically":[59],"creating":[60],"to":[63,97,110,142,162],"be":[64],"used":[65,121,149],"augmentation,":[71],"on":[72,94],"other":[74],"hand,":[75],"adults'":[76,95,104,117],"pooled":[79],"together":[80],"with":[81],"speech.":[83,114],"At":[84],"same":[86],"time,":[87],"voice":[88],"conversion":[89],"(VC)":[90],"also":[92],"applied":[93],"alter":[98],"acoustic":[100],"attributes.":[101],"VC":[102],"makes":[106],"it":[107],"perceptually":[108],"similar":[109],"The":[115,124,154],"converted":[116],"then":[120],"ASV":[125],"systems":[126],"developed":[127],"study":[130],"employ":[131],"x-vectors":[132],"derived":[133],"using":[134],"time-delay":[136],"deep":[137],"neural":[138],"network.":[139],"addition":[141],"that,":[143],"probabilistic":[144],"linear":[145],"discriminant":[146],"analysis":[147],"scoring":[151],"performance.":[153],"explored":[155],"methods":[156],"noted":[161],"reduce":[163],"equal":[165],"error":[166],"rate":[167],"as":[168,170],"well":[169],"minimum":[171],"decision":[172],"cost":[173],"function":[174],"by":[175],"large":[177],"margin.":[178]},"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":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}