{"id":"https://openalex.org/W3082603178","doi":"https://doi.org/10.1109/spcom50965.2020.9179497","title":"Improving Automatic Speech Recognition by Classifying Adult and Child Speakers into Separate Groups using Speech Rate Rhythmicity Parameter","display_name":"Improving Automatic Speech Recognition by Classifying Adult and Child Speakers into Separate Groups using Speech Rate Rhythmicity Parameter","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3082603178","doi":"https://doi.org/10.1109/spcom50965.2020.9179497","mag":"3082603178"},"language":"en","primary_location":{"id":"doi:10.1109/spcom50965.2020.9179497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom50965.2020.9179497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Signal Processing and Communications (SPCOM)","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/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":true,"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/A5057514953","display_name":"Tarun Sai Bandarupalli","orcid":null},"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":"Tarun Sai Bandarupalli","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":"last","author":{"id":"https://openalex.org/A5064721564","display_name":"Raghav Chakravarthy","orcid":null},"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":"R Chakravarthy","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":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063682063"],"corresponding_institution_ids":["https://openalex.org/I11793825"],"apc_list":null,"apc_paid":null,"fwci":0.5302,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7287199,"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":"5"},"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":0.9991000294685364,"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":0.9984999895095825,"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":0.8049554228782654},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7378512024879456},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7019819021224976},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5192208886146545},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.48254722356796265},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35541868209838867}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8049554228782654},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7378512024879456},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7019819021224976},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5192208886146545},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.48254722356796265},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35541868209838867}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/spcom50965.2020.9179497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom50965.2020.9179497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Signal Processing and Communications (SPCOM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4399999976158142,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W23783389","https://openalex.org/W160885690","https://openalex.org/W1512098439","https://openalex.org/W1524333225","https://openalex.org/W1540779870","https://openalex.org/W1761922146","https://openalex.org/W1996159834","https://openalex.org/W2056914870","https://openalex.org/W2064675550","https://openalex.org/W2079032785","https://openalex.org/W2100118853","https://openalex.org/W2115002762","https://openalex.org/W2127894527","https://openalex.org/W2130722890","https://openalex.org/W2151040995","https://openalex.org/W2155941368","https://openalex.org/W2160815625","https://openalex.org/W2162672997","https://openalex.org/W2164931619","https://openalex.org/W2184045248","https://openalex.org/W2402172738","https://openalex.org/W2757257005","https://openalex.org/W4230184039","https://openalex.org/W6630527977","https://openalex.org/W6631362777"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2368768466","https://openalex.org/W2757081366","https://openalex.org/W2640905660"],"abstract_inverted_index":{"When":[0],"children's":[1,36,163],"speech":[2,26,30,130,164],"is":[3,17,68,92,139,177,182],"transcribed":[4],"using":[5,27,44],"acoustic":[6],"models":[7],"trained":[8,34,169],"on":[9,23,35,94,166],"adults'":[10,25],"data,":[11],"a":[12,79,128,184],"severely":[13],"degraded":[14],"recognition":[15,31,156,165],"performance":[16],"obtained.":[18],"Similar":[19],"degradations":[20],"are":[21,111],"noted":[22],"recognizing":[24],"an":[28,59],"automatic":[29],"(ASR)":[32],"system":[33],"speech.":[37],"This":[38],"problem":[39],"can":[40,133,149,171],"be":[41,134,151,172],"overcome":[42],"by":[43,122],"two":[45,51,117],"separate":[46],"ASR":[47,147],"systems":[48,148,170],"for":[49,102,115,127,161],"the":[50,65,87,100,108,116,124,180],"groups":[52,118],"of":[53,119],"speakers.":[54,120],"But":[55],"this":[56,75,195],"approach":[57,91],"requires":[58],"effective":[60],"technique":[61,84],"to":[62,85,153],"detect":[63],"whether":[64,137],"given":[66,129],"data":[67,168,181],"from":[69,140,183],"adult":[70,141,167],"or":[71,142],"child":[72,143,185],"speaker.":[73,144,186],"In":[74],"paper,":[76],"we":[77],"present":[78],"very":[80,113],"simple":[81],"and":[82,104],"novel":[83],"do":[86],"same.":[88],"The":[89,145],"proposed":[90],"based":[93],"speechrate":[95],"rhythmicity":[96],"parameter":[97],"(SRRP).":[98],"Since":[99],"speaking-rates":[101],"adults":[103],"children":[105],"differ":[106],"significantly,":[107],"SRRP":[109,125],"values":[110],"also":[112],"different":[114],"Hence,":[121],"computing":[123],"value":[126],"utterance,":[131],"it":[132,138,176],"easily":[135],"determined":[136],"corresponding":[146],"then":[150],"used":[152],"achieve":[154],"improved":[155],"performance.":[157],"Alternatively,":[158],"existing":[159],"techniques":[160],"improving":[162],"directly":[173],"applied":[174],"once":[175],"known":[178],"that":[179],"Both":[187],"these":[188],"aspects":[189],"have":[190],"been":[191],"experimentally":[192],"validated":[193],"in":[194],"work.":[196]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}