{"id":"https://openalex.org/W2891029097","doi":"https://doi.org/10.1109/icassp.2018.8461668","title":"Role of Prosodic Features on Children's Speech Recognition","display_name":"Role of Prosodic Features on Children's Speech Recognition","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2891029097","doi":"https://doi.org/10.1109/icassp.2018.8461668","mag":"2891029097"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5003438160","display_name":"Hemant Kumar Kathania","orcid":"https://orcid.org/0000-0002-6367-5203"},"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":true,"raw_author_name":"Hemant K. Kathania","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"]}]},{"author_position":"middle","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":false,"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/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/A5070407855","display_name":"Waquar Ahmad","orcid":"https://orcid.org/0000-0001-7817-3313"},"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":false,"raw_author_name":"Waquar Ahmad","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"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5003438160"],"corresponding_institution_ids":["https://openalex.org/I101326570"],"apc_list":null,"apc_paid":null,"fwci":1.466,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.86687637,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"1","issue":null,"first_page":"5519","last_page":"5523"},"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":0.9976999759674072,"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":0.9945999979972839,"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":0.814738392829895},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7477118372917175},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7169085144996643},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.606015145778656},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49942612648010254},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4906364977359772},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.4831185042858124},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45037639141082764},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.4360581636428833},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42252814769744873},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3934967815876007},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3665999472141266},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08378741145133972}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.814738392829895},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7477118372917175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7169085144996643},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.606015145778656},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49942612648010254},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4906364977359772},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.4831185042858124},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45037639141082764},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.4360581636428833},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42252814769744873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3934967815876007},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3665999472141266},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08378741145133972},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W148091393","https://openalex.org/W185318337","https://openalex.org/W205402702","https://openalex.org/W1524333225","https://openalex.org/W1540779870","https://openalex.org/W1590070522","https://openalex.org/W1994888226","https://openalex.org/W2015894840","https://openalex.org/W2066972841","https://openalex.org/W2085662862","https://openalex.org/W2090861223","https://openalex.org/W2094954292","https://openalex.org/W2100118853","https://openalex.org/W2106554350","https://openalex.org/W2108877721","https://openalex.org/W2115002762","https://openalex.org/W2131703294","https://openalex.org/W2147768505","https://openalex.org/W2148154194","https://openalex.org/W2150919661","https://openalex.org/W2152131029","https://openalex.org/W2243512965","https://openalex.org/W2295983515","https://openalex.org/W2338914793","https://openalex.org/W2402172738","https://openalex.org/W2402844907","https://openalex.org/W2426479676","https://openalex.org/W2487211121","https://openalex.org/W2507923760","https://openalex.org/W2657982891","https://openalex.org/W4244494905","https://openalex.org/W4301288833","https://openalex.org/W6631362777","https://openalex.org/W6635193370","https://openalex.org/W6654160615","https://openalex.org/W6677005180","https://openalex.org/W6682236695","https://openalex.org/W6682620333","https://openalex.org/W6683907119","https://openalex.org/W6690523614","https://openalex.org/W6697215464","https://openalex.org/W6703681455","https://openalex.org/W6713111094","https://openalex.org/W6739502070"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W1556565948","https://openalex.org/W4317383455","https://openalex.org/W2548511587"],"abstract_inverted_index":{"In":[0],"this":[1,61,146],"paper,":[2],"we":[3],"have":[4],"explored":[5,32],"the":[6,13,18,48,67,71,73,87,90,96,106,111,117,126,132],"role":[7],"of":[8,20,102,169],"combining":[9,131,160],"prosodic":[10,50,75,103,164],"variables":[11,51,76],"with":[12],"existing":[14],"acoustic":[15,25,33],"features":[16,34,134],"in":[17,60,145],"context":[19,97],"children's":[21,84,176],"speech":[22,150,177],"recognition":[23,118,151],"using":[24,152,178],"models":[26],"trained":[27,181],"on":[28,174],"adults'":[29,82],"speech.":[30,85],"The":[31,139],"are":[35,52,122],"Mel-frequency":[36],"cepstral":[37,44],"coefficients":[38,45],"(MFCC)":[39],"and":[40,55,83,109,163],"perceptual":[41],"linear":[42],"prediction":[43],"(PLPCC)":[46,162],"while":[47],"considered":[49,74],"loudness,":[53],"voice-intensity":[54],"voice-probability.":[56],"An":[57],"analysis":[58],"presented":[59],"paper":[62],"shows":[63],"that,":[64],"given":[65],"that":[66],"textual":[68],"content":[69],"remains":[70],"same,":[72],"exhibit":[77],"very":[78],"similar":[79],"contours":[80,91],"for":[81,148],"At":[86],"same":[88,140],"time,":[89],"differ":[92],"a":[93,136,166],"lot":[94],"when":[95],"is":[98,172],"different.":[99],"Consequently,":[100],"inclusion":[101],"information":[104],"reduces":[105],"inter-speaker":[107],"differences":[108],"increases":[110],"class":[112],"discrimination.":[113],"This":[114],"subsequently":[115],"improves":[116],"performance.":[119],"Further":[120],"improvements":[121],"obtained":[123,129],"by":[124,130],"projecting":[125],"feature":[127],"vectors":[128],"two":[133],"to":[135],"lower-dimensional":[137],"subspace.":[138],"has":[141],"been":[142],"experimentally":[143],"verified":[144],"study":[147],"mismatched":[149],"deep":[153],"neural":[154],"network":[155],"(DNN)":[156],"based":[157],"system.":[158],"On":[159],"MFCC":[161],"features,":[165],"relative":[167],"improvement":[168],"16%":[170],"(14%)":[171],"noted":[173],"decoding":[175],"adult":[179],"data":[180],"DNN":[182],"models.":[183]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}