{"id":"https://openalex.org/W3162425752","doi":"https://doi.org/10.1109/icassp39728.2021.9413930","title":"Towards Data Selection on TTS Data for Children\u2019s Speech Recognition","display_name":"Towards Data Selection on TTS Data for Children\u2019s Speech Recognition","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162425752","doi":"https://doi.org/10.1109/icassp39728.2021.9413930","mag":"3162425752"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100391659","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0001-5367-7056"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102974956","display_name":"Zhikai Zhou","orcid":"https://orcid.org/0000-0002-4626-2677"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhikai Zhou","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103070663","display_name":"Yizhou Lu","orcid":"https://orcid.org/0000-0003-1399-8079"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhou Lu","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101406825","display_name":"Hongji Wang","orcid":"https://orcid.org/0000-0002-8834-1592"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongji Wang","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035532752","display_name":"Chenpeng Du","orcid":"https://orcid.org/0000-0001-5329-0847"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenpeng Du","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6888","last_page":"6892"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9977999925613403,"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":0.9965999722480774,"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/speech-recognition","display_name":"Speech recognition","score":0.7401743531227112},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7308541536331177},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6527666449546814},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39471328258514404},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.386263906955719}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7401743531227112},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7308541536331177},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6527666449546814},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39471328258514404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.386263906955719}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7599999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2066972841","https://openalex.org/W2120847449","https://openalex.org/W2150769028","https://openalex.org/W2168510624","https://openalex.org/W2526425061","https://openalex.org/W2533523411","https://openalex.org/W2626778328","https://openalex.org/W2627092829","https://openalex.org/W2739883972","https://openalex.org/W2747024632","https://openalex.org/W2801580204","https://openalex.org/W2936774411","https://openalex.org/W2963979492","https://openalex.org/W2972389417","https://openalex.org/W2972432827","https://openalex.org/W2972594541","https://openalex.org/W2972811785","https://openalex.org/W2972841547","https://openalex.org/W3008480565","https://openalex.org/W3015611303","https://openalex.org/W3016160783","https://openalex.org/W3024464021","https://openalex.org/W3033411150","https://openalex.org/W3107298252","https://openalex.org/W4385245566","https://openalex.org/W6631362777","https://openalex.org/W6728841359","https://openalex.org/W6739901393","https://openalex.org/W6751191447","https://openalex.org/W6778823374"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Although":[0],"great":[1],"progress":[2],"has":[3],"been":[4,41],"made":[5,42],"on":[6,132,189],"automatic":[7],"speech":[8,13,25,55,69,89,100],"recognition":[9,14,90],"(ASR)":[10],"systems,":[11],"children\u2019s":[12,24,35,68,88,96,106,149],"still":[15],"remains":[16],"a":[17,71],"challenging":[18],"task.":[19],"General":[20],"ASR":[21,57,113,150],"systems":[22],"for":[23,56,148,174],"suffer":[26],"from":[27],"the":[28,65,85,95,112,133,138,141,155,165,185],"lack":[29],"of":[30,67,87,109,140],"corpora":[31],"and":[32,36,111,137,170,177],"mismatch":[33,46],"between":[34],"adults\u2019":[37,54,61],"speech.":[38],"Efforts":[39],"have":[40],"to":[43,51,70,83,105,184],"reduce":[44],"such":[45],"by":[47],"applying":[48],"normalization":[49],"methods":[50],"generate":[52],"modified":[53,60],"training.":[58],"However,":[59],"data":[62,81,129,143,160],"can":[63,144,163],"reflect":[64],"characteristics":[66],"very":[72],"limited":[73],"extent.":[74],"In":[75],"this":[76,125],"work,":[77],"we":[78,127],"adopt":[79],"text-to-speech":[80],"augmentation":[82],"improve":[84],"performance":[86],"system.":[91],"We":[92,152],"find":[93],"that":[94,154],"TTS":[97,134],"model":[98,187],"generates":[99],"with":[101,118],"inconsistent":[102],"quality":[103],"due":[104],"substandard":[107],"pronunciations":[108],"phonemes,":[110],"system":[114],"suffers":[115],"when":[116],"trained":[117,188],"these":[119],"additional":[120],"synthesized":[121,142],"data.":[122,191],"To":[123],"solve":[124],"problem,":[126],"propose":[128],"selection":[130,161],"strategies":[131],"augmented":[135],"data,":[136],"effectiveness":[139],"be":[145],"substantially":[146],"boosted":[147],"modeling.":[151],"show":[153],"speaker":[156],"embedding":[157],"similarity":[158],"based":[159],"strategy":[162],"obtain":[164],"best":[166],"position:":[167],"relative":[168],"14.0%":[169],"14.7%":[171],"CER":[172],"reduction":[173],"child":[175,178],"conversation":[176],"reading":[179],"test":[180],"set":[181],"respectively":[182],"compared":[183],"baseline":[186],"real":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}