{"id":"https://openalex.org/W2944097536","doi":"https://doi.org/10.1109/iscslp.2018.8706703","title":"A Study on Acoustic Modeling for Child Speech Based on Multi-Task Learning","display_name":"A Study on Acoustic Modeling for Child Speech Based on Multi-Task Learning","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2944097536","doi":"https://doi.org/10.1109/iscslp.2018.8706703","mag":"2944097536"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2018.8706703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5100639354","display_name":"Jiarui Wang","orcid":"https://orcid.org/0000-0002-2138-6016"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiarui Wang","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110724403","display_name":"Si Ioi Ng","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Si Ioi Ng","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034779277","display_name":"Dehua Tao","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dehua Tao","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010166231","display_name":"Wing Yee Ng","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wing Yee Ng","raw_affiliation_strings":["Division of Speech Therapy, The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Division of Speech Therapy, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001795601","display_name":"Tan Lee","orcid":"https://orcid.org/0000-0002-7089-3436"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tan Lee","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100639354"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":1.3031,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.8587324,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"35","issue":null,"first_page":"389","last_page":"393"},"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":0.995199978351593,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8176887035369873},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7738268375396729},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6242494583129883},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5978291630744934},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5675688982009888},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5506826639175415},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5420525670051575},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5280390977859497},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5203170776367188},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5061213374137878},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.46853509545326233},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4651324152946472},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46431848406791687},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4347080588340759},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.43307533860206604},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40793099999427795},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.2540872395038605},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07666012644767761},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07099586725234985}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8176887035369873},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7738268375396729},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6242494583129883},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5978291630744934},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5675688982009888},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5506826639175415},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5420525670051575},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5280390977859497},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5203170776367188},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5061213374137878},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.46853509545326233},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4651324152946472},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46431848406791687},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4347080588340759},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.43307533860206604},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40793099999427795},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2540872395038605},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07666012644767761},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07099586725234985},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2018.8706703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W434092020","https://openalex.org/W1482605500","https://openalex.org/W1510862247","https://openalex.org/W1524333225","https://openalex.org/W2020625684","https://openalex.org/W2026369565","https://openalex.org/W2041823554","https://openalex.org/W2048526313","https://openalex.org/W2056638738","https://openalex.org/W2066972841","https://openalex.org/W2072563337","https://openalex.org/W2074428136","https://openalex.org/W2117130368","https://openalex.org/W2164851408","https://openalex.org/W2295983515","https://openalex.org/W2398423749","https://openalex.org/W2402146185","https://openalex.org/W2519224033","https://openalex.org/W2610458980","https://openalex.org/W2747681982","https://openalex.org/W2747764356","https://openalex.org/W2792175982","https://openalex.org/W2801580204","https://openalex.org/W3007928779","https://openalex.org/W6615059388","https://openalex.org/W6628911050","https://openalex.org/W6630566170","https://openalex.org/W6631362777","https://openalex.org/W6656895381","https://openalex.org/W6697215464","https://openalex.org/W6712825807","https://openalex.org/W6712930963","https://openalex.org/W6751191447"],"related_works":["https://openalex.org/W2061937230","https://openalex.org/W2132658536","https://openalex.org/W3081187864","https://openalex.org/W151018310","https://openalex.org/W4380605396","https://openalex.org/W4298261218","https://openalex.org/W3133352777","https://openalex.org/W2008737763","https://openalex.org/W2784059283","https://openalex.org/W2291624303"],"abstract_inverted_index":{"This":[0,17],"paper":[1],"describes":[2],"a":[3,24,72,87,100,105],"study":[4,18],"on":[5],"acoustic":[6,32,147],"modeling":[7,119],"of":[8,15,63,90,130,162,180],"child":[9,66,121],"speech":[10,13,26,36,43,67,75,84,122,125,132,139],"for":[11,30,35,86,120],"large-vocabulary":[12],"recognition":[14,76],"Cantonese.":[16],"is":[19,68,79,96,175],"driven":[20],"and":[21,104,113,123,152,183,188],"enabled":[22],"by":[23,52],"new":[25],"corpus":[27],"recently":[28],"collected":[29],"developing":[31],"assessment":[33],"systems":[34],"sound":[37],"disorders":[38],"in":[39,57,172],"Cantonese-speaking":[40],"children.":[41],"The":[42,111,127,166],"corpus,":[44],"named":[45],"CUChild127,":[46],"contains":[47],"127":[48],"Chinese":[49],"words":[50],"spoken":[51],"1,":[53],"500":[54],"pre-school":[55],"children":[56],"Hong":[58],"Kong.":[59],"A":[60],"small":[61],"amount":[62,89],"manually":[64],"transcribed":[65],"used":[69,81],"to":[70,82,98,158],"initialize":[71],"GMM-HMM":[73,153],"based":[74,146],"system,":[77],"which":[78],"subsequently":[80],"generate":[83],"transcriptions":[85],"large":[88],"training":[91,128],"data.":[92],"Multi-task":[93,155],"learning":[94,156],"approach":[95],"adopted":[97],"train":[99],"conventional":[101],"DNN":[102,151],"model":[103,148],"time-delay":[106],"neural":[107],"network":[108],"(TDNN)":[109],"model.":[110,165],"primary":[112,182],"secondary":[114,184],"tasks":[115,185],"are":[116,133],"context-dependent":[117],"phone":[118],"adult":[124,131],"respectively.":[126],"data":[129],"obtained":[134],"from":[135],"an":[136],"existing":[137],"phonetically-rich":[138],"corpus.":[140],"Experimental":[141],"results":[142],"show":[143],"that":[144],"TDNN":[145,164],"significantly":[149],"outperforms":[150],"systems.":[154],"leads":[157],"further":[159],"performance":[160],"improvement":[161],"the":[163,178,181],"best":[167],"syllable":[168],"error":[169],"rate":[170],"attained":[171],"our":[173],"experiments":[174],"8.96%,":[176],"with":[177],"weights":[179],"being":[186],"0.8":[187],"0.2.":[189]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}