{"id":"https://openalex.org/W2765133218","doi":"https://doi.org/10.1109/ncc.2017.8077101","title":"Acoustic and language modeling for children's read speech assessment","display_name":"Acoustic and language modeling for children's read speech assessment","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2765133218","doi":"https://doi.org/10.1109/ncc.2017.8077101","mag":"2765133218"},"language":"en","primary_location":{"id":"doi:10.1109/ncc.2017.8077101","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc.2017.8077101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Twenty-third National Conference on Communications (NCC)","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/A5065684433","display_name":"Hitesh Tulsiani","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Hitesh Tulsiani","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology, Bombay, India"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology, Bombay, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061375051","display_name":"Prakhar Swarup","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prakhar Swarup","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology, Bombay, India"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology, Bombay, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084496610","display_name":"Preeti Rao","orcid":"https://orcid.org/0000-0002-2842-8450"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Preeti Rao","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology, Bombay, India"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology, Bombay, India","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5065684433"],"corresponding_institution_ids":["https://openalex.org/I162827531"],"apc_list":null,"apc_paid":null,"fwci":0.2064,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.63250175,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9987999796867371,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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":0.8223693370819092},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7239737510681152},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5566554069519043},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.5511299967765808},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5334396958351135},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5315373539924622},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.47875991463661194},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4740559756755829},{"id":"https://openalex.org/keywords/reading-aloud","display_name":"Reading aloud","score":0.44228994846343994},{"id":"https://openalex.org/keywords/literacy","display_name":"Literacy","score":0.43539321422576904},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4347195327281952},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.43087756633758545},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40352967381477356},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39686092734336853},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2548772096633911},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11769327521324158},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11455908417701721}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8223693370819092},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7239737510681152},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5566554069519043},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.5511299967765808},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5334396958351135},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5315373539924622},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.47875991463661194},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4740559756755829},{"id":"https://openalex.org/C2993756790","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading aloud","level":3,"score":0.44228994846343994},{"id":"https://openalex.org/C547764534","wikidata":"https://www.wikidata.org/wiki/Q8236","display_name":"Literacy","level":2,"score":0.43539321422576904},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4347195327281952},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.43087756633758545},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40352967381477356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39686092734336853},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2548772096633911},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11769327521324158},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11455908417701721},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ncc.2017.8077101","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc.2017.8077101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Twenty-third National Conference on Communications (NCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8999999761581421,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W44088289","https://openalex.org/W44638342","https://openalex.org/W1501139663","https://openalex.org/W1524333225","https://openalex.org/W1582482241","https://openalex.org/W1635512741","https://openalex.org/W1994888226","https://openalex.org/W2002342963","https://openalex.org/W2087459182","https://openalex.org/W2106119541","https://openalex.org/W2120316500","https://openalex.org/W2135582271","https://openalex.org/W2145155465","https://openalex.org/W2165357419","https://openalex.org/W6601808394","https://openalex.org/W6631362777","https://openalex.org/W6677994422"],"related_works":["https://openalex.org/W2126322296","https://openalex.org/W2163537793","https://openalex.org/W2037769829","https://openalex.org/W2916997151","https://openalex.org/W2781555308","https://openalex.org/W3021690593","https://openalex.org/W2125343999","https://openalex.org/W4200200210","https://openalex.org/W2161188302","https://openalex.org/W2888189389"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,12,103],"recognition":[2],"can":[3,58],"be":[4],"used":[5,109],"to":[6,110,130],"evaluate":[7],"the":[8,24,31,37,43,50,68,72,89,99,114,120,124],"accuracy":[9],"of":[10,33,40,45,52,74,101,119,126,146],"read":[11],"and":[13,54,104,112,149],"thus":[14],"serve":[15],"a":[16,60,83,142],"valuable":[17],"role":[18,62],"in":[19,30,42,63,67,77,80,88],"literacy":[20],"development":[21],"by":[22,86],"providing":[23],"needed":[25],"feedback":[26],"on":[27,141],"reading":[28],"skills":[29],"absence":[32],"qualified":[34],"teachers.":[35],"Given":[36],"known":[38],"limitations":[39],"ASR":[41],"face":[44],"insufficient":[46],"task-specific":[47],"training":[48],"data,":[49],"selection":[51],"acoustic":[53,115],"language":[55,134],"modeling":[56],"strategies":[57],"play":[59],"crucial":[61],"achieving":[64],"acceptable":[65],"performance":[66,140],"task.":[69],"We":[70,136],"consider":[71],"problem":[73],"detecting":[75],"mispronunciations":[76],"read-aloud":[78],"stories":[79],"English":[81,107],"(as":[82],"second":[84],"language)":[85],"children":[87],"age":[90],"group":[91],"10-14.":[92],"Multiple":[93],"available":[94],"datasets":[95],"that":[96],"separately":[97],"capture":[98],"characteristics":[100],"children's":[102],"Indian":[105],"accented":[106],"are":[108],"train":[111],"adapt":[113],"models.":[116],"A":[117],"knowledge":[118],"text":[121],"together":[122],"with":[123],"prediction":[125],"mispronunciation":[127,138],"errors":[128],"helps":[129],"define":[131],"an":[132],"effective":[133],"model.":[135],"present":[137],"detection":[139],"small":[143],"test":[144],"dataset":[145],"field":[147],"recordings":[148],"discuss":[150],"implications":[151],"for":[152],"further":[153],"work.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
