{"id":"https://openalex.org/W4392904341","doi":"https://doi.org/10.1109/icassp48485.2024.10445913","title":"Build a 50+ Hours Chinese Mandarin Corpus for Children\u2019s Speech Recognition","display_name":"Build a 50+ Hours Chinese Mandarin Corpus for Children\u2019s Speech Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904341","doi":"https://doi.org/10.1109/icassp48485.2024.10445913"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445913","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10445913","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5100641494","display_name":"Hao Xu","orcid":"https://orcid.org/0000-0001-7759-2620"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Xu","raw_affiliation_strings":["East China Normal University,School of Data Science &#x0026; Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,School of Data Science &#x0026; Engineering,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017371862","display_name":"Jing Yang","orcid":"https://orcid.org/0000-0002-2565-0574"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Yang","raw_affiliation_strings":["East China Normal University,School of Data Science &#x0026; Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,School of Data Science &#x0026; Engineering,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329217","display_name":"Jiahao Wang","orcid":"https://orcid.org/0000-0002-4268-8021"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahao Wang","raw_affiliation_strings":["East China Normal University,School of Data Science &#x0026; Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,School of Data Science &#x0026; Engineering,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101578643","display_name":"Wenxin Hu","orcid":"https://orcid.org/0000-0001-8137-620X"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxin Hu","raw_affiliation_strings":["East China Normal University,School of Computer Science and Technology,Shanghai,China","School of Computer Science and Technology, East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I66867065"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"10231","last_page":"10235"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9951000213623047,"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":0.9848999977111816,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.779660701751709},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7664985656738281},{"id":"https://openalex.org/keywords/pinyin","display_name":"Pinyin","score":0.756732702255249},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7293164730072021},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6707348823547363},{"id":"https://openalex.org/keywords/chinese-speech-synthesis","display_name":"Chinese speech synthesis","score":0.6440690159797668},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5610612034797668},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5161793828010559},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3863690495491028},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.2859271764755249},{"id":"https://openalex.org/keywords/chinese-characters","display_name":"Chinese characters","score":0.24023771286010742},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1171548068523407}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.779660701751709},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7664985656738281},{"id":"https://openalex.org/C2781095461","wikidata":"https://www.wikidata.org/wiki/Q42222","display_name":"Pinyin","level":3,"score":0.756732702255249},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7293164730072021},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6707348823547363},{"id":"https://openalex.org/C73411735","wikidata":"https://www.wikidata.org/wiki/Q16369","display_name":"Chinese speech synthesis","level":4,"score":0.6440690159797668},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5610612034797668},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5161793828010559},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3863690495491028},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2859271764755249},{"id":"https://openalex.org/C2781051154","wikidata":"https://www.wikidata.org/wiki/Q8201","display_name":"Chinese characters","level":2,"score":0.24023771286010742},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1171548068523407},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445913","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10445913","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322370","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W88545716","https://openalex.org/W160885690","https://openalex.org/W1994888226","https://openalex.org/W2066972841","https://openalex.org/W2094954292","https://openalex.org/W2397674163","https://openalex.org/W2936774411","https://openalex.org/W2963242190","https://openalex.org/W2998376432","https://openalex.org/W3036601975","https://openalex.org/W3076645148","https://openalex.org/W3097017391","https://openalex.org/W3097777922","https://openalex.org/W3100684970","https://openalex.org/W3162425752","https://openalex.org/W3163842018","https://openalex.org/W4206789583","https://openalex.org/W4248048444","https://openalex.org/W4281633595","https://openalex.org/W4283067311","https://openalex.org/W4286527731","https://openalex.org/W4288391450","https://openalex.org/W4297841705","https://openalex.org/W4385822407","https://openalex.org/W4385823039","https://openalex.org/W6615059388","https://openalex.org/W6761176036","https://openalex.org/W6780218876","https://openalex.org/W6796554684","https://openalex.org/W6802061202"],"related_works":["https://openalex.org/W4214677368","https://openalex.org/W2599178495","https://openalex.org/W4312354763","https://openalex.org/W2547767923","https://openalex.org/W2741769689","https://openalex.org/W2529685800","https://openalex.org/W3191624196","https://openalex.org/W3204158272","https://openalex.org/W4296721027","https://openalex.org/W2787859844"],"abstract_inverted_index":{"Children\u2019s":[0],"speech":[1,16,26,37,53,89,93,109,124],"recognition":[2,17,27,125],"plays":[3],"an":[4],"important":[5],"role":[6],"in":[7,23],"the":[8,33,62,75,98,136,167,176,188],"education":[9],"research":[10,83],"of":[11,25,35,48,56,66,81,158,190],"children.":[12],"The":[13,79],"usual":[14],"automatic":[15],"(ASR)":[18],"systems":[19],"are":[20,58],"not":[21],"satisfactory":[22],"terms":[24],"for":[28,91],"children,":[29],"mainly":[30],"due":[31],"to":[32,85,104,113,133],"lack":[34],"child":[36],"corpus.":[38],"In":[39],"recent":[40],"years,":[41],"there":[42],"have":[43],"been":[44],"a":[45,87,122,131,156,183],"large":[46],"number":[47],"related":[49],"studies":[50],"on":[51,61,175,187],"children\u2019s":[52,88,92,99,108,148,162],"recognition,":[54],"most":[55],"which":[57,74],"improved":[59],"based":[60],"existing":[63],"small":[64],"amount":[65],"data":[67,69,110,144,177],"through":[68,121],"augmentation,":[70],"transfer":[71],"learning,":[72],"etc,":[73],"promotion":[76],"is":[77,84],"limited.":[78],"purpose":[80],"our":[82],"establish":[86],"corpus":[90,157],"recognition.":[94],"Firstly,":[95],"we":[96,178],"use":[97],"language":[100],"proficiency":[101],"assessment":[102],"system":[103],"collect":[105],"weakly":[106],"labeled":[107],"from":[111],"3":[112],"12":[114],"years":[115],"old,":[116],"and":[117,139,150,154,180],"obtain":[118],"transcribed":[119,137],"text":[120],"commercial-grade":[123],"interface.":[126],"Then,":[127],"this":[128],"paper":[129],"proposes":[130],"method":[132],"quickly":[134],"verify":[135],"text,":[138],"screens":[140],"out":[141],"effective":[142],"label":[143],"pairs":[145],"by":[146],"combining":[147],"pronunciation":[149],"Chinese":[151],"pinyin":[152],"characteristics,":[153],"constructs":[155],"50+":[159],"hours":[160],"Mandarin":[161],"speech.":[163],"We":[164],"experimented":[165],"with":[166],"current":[168],"mainstream":[169],"mandarin\u2019s":[170],"end-to-end":[171],"pretrained":[172],"model,":[173],"finetuning":[174],"built,":[179],"can":[181],"achieve":[182],"15%":[184],"CER":[185],"reduction":[186],"basis":[189],"baseline":[191],"without":[192],"using":[193],"finetuning.":[194]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
