{"id":"https://openalex.org/W2947791728","doi":"https://doi.org/10.1109/spcom.2018.8724465","title":"Improving Children's Speech Recognition Through Time Scale Modification Based Speaking Rate Adaptation","display_name":"Improving Children's Speech Recognition Through Time Scale Modification Based Speaking Rate Adaptation","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2947791728","doi":"https://doi.org/10.1109/spcom.2018.8724465","mag":"2947791728"},"language":"en","primary_location":{"id":"doi:10.1109/spcom.2018.8724465","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom.2018.8724465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/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/A5070407855","display_name":"Waquar Ahmad","orcid":"https://orcid.org/0000-0001-7817-3313"},"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":false,"raw_author_name":"Waquar Ahmad","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/A5028597938","display_name":"Nagraj Adiga","orcid":null},"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":"Nagraj 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":"middle","author":{"id":"https://openalex.org/A5016425387","display_name":"Suman Jana","orcid":"https://orcid.org/0000-0002-9850-2169"},"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":false,"raw_author_name":"S. K. Jana","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":"last","author":{"id":"https://openalex.org/A5057711093","display_name":"Arindam Samaddar","orcid":"https://orcid.org/0000-0002-2985-6190"},"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":false,"raw_author_name":"A. B. Samaddar","raw_affiliation_strings":["Department of Computer Science and Engineering, NIT, Sikkim, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, NIT, Sikkim, India","institution_ids":["https://openalex.org/I101326570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5003438160"],"corresponding_institution_ids":["https://openalex.org/I101326570"],"apc_list":null,"apc_paid":null,"fwci":0.6515,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.78176181,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"257","last_page":"261"},"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":0.9998000264167786,"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":0.9959999918937683,"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/vocal-tract","display_name":"Vocal tract","score":0.8275465965270996},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7457149624824524},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6702466607093811},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6560395956039429},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.649716854095459},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6245813369750977},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5261040329933167},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4994525909423828},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.45470839738845825},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1653139293193817},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11164575815200806}],"concepts":[{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.8275465965270996},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7457149624824524},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6702466607093811},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6560395956039429},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.649716854095459},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6245813369750977},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5261040329933167},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4994525909423828},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45470839738845825},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1653139293193817},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11164575815200806},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/spcom.2018.8724465","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom.2018.8724465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Conference on Signal Processing and Communications (SPCOM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/1","display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W132121590","https://openalex.org/W160885690","https://openalex.org/W173400130","https://openalex.org/W192280404","https://openalex.org/W1524333225","https://openalex.org/W1532531043","https://openalex.org/W1540779870","https://openalex.org/W1994888226","https://openalex.org/W2010362084","https://openalex.org/W2066159843","https://openalex.org/W2066972841","https://openalex.org/W2094954292","https://openalex.org/W2100118853","https://openalex.org/W2112021726","https://openalex.org/W2115008841","https://openalex.org/W2130722890","https://openalex.org/W2151534206","https://openalex.org/W2158215783","https://openalex.org/W2159300614","https://openalex.org/W2160815625","https://openalex.org/W2163089518","https://openalex.org/W2164931619","https://openalex.org/W2276408190","https://openalex.org/W2338914793","https://openalex.org/W2402172738","https://openalex.org/W2507923760","https://openalex.org/W2587488139","https://openalex.org/W2736786568","https://openalex.org/W2747399100","https://openalex.org/W2755431812","https://openalex.org/W2766853512","https://openalex.org/W6605448002","https://openalex.org/W6606647699","https://openalex.org/W6631362777","https://openalex.org/W6631949791","https://openalex.org/W6703681455","https://openalex.org/W6741240231","https://openalex.org/W6744394073","https://openalex.org/W6745661829"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W2942893872","https://openalex.org/W1911592522","https://openalex.org/W2087669554","https://openalex.org/W3044757496"],"abstract_inverted_index":{"In":[0],"the":[1,10,31,34,49,67,72,101,131,166,169,191],"work":[2],"presented":[3,89],"in":[4,55,74,130,160],"this":[5],"paper,":[6],"we":[7,125],"have":[8,84,88,99,126],"explored":[9,127,192],"effect":[11,170],"of":[12,33,82,92,103,133,171],"speaking-rate":[13,104,128,156,173,195],"adaptation":[14,105,129,174],"on":[15,23,106,115,148],"children's":[16,53,107],"speech":[17,54,108],"recognition":[18,50],"using":[19,144],"acoustic":[20,68,140],"models":[21],"trained":[22],"adults'":[24],"speech.":[25],"It":[26],"is":[27,59,153,182],"well":[28],"known":[29],"that,":[30],"shape":[32],"vocal":[35],"organs,":[36],"pitch":[37,75,180],"and":[38,45,76,179],"speaking-rates":[39],"are":[40,162,187],"significantly":[41],"different":[42],"for":[43,52,155],"adult":[44],"child":[46],"speakers.":[47],"Consequently,":[48],"performance":[51],"such":[56],"mismatched":[57],"setup":[58],"reported":[60,86],"to":[61],"be":[62],"extremely":[63],"poor.":[64],"To":[65],"address":[66],"mismatch":[69],"resulting":[70],"from":[71],"differences":[73],"vocal-tract":[77,176],"geometry,":[78],"a":[79,90,96],"large":[80],"number":[81],"studies":[83,112],"been":[85],"that":[87],"myriad":[91],"techniques.":[93],"But,":[94],"only":[95],"few":[97],"works":[98],"studied":[100],"role":[102],"recognition.":[109],"Furthermore,":[110,168],"those":[111],"were":[113],"performed":[114],"systems":[116,134],"employing":[117,135],"Gaussian":[118],"mixture":[119],"models.":[120],"Motivated":[121],"by":[122,164,189],"these":[123],"facts,":[124],"context":[132],"deep":[136],"neural":[137],"network":[138],"based":[139,147],"modeling.":[141],"Time-scale":[142],"modification":[143],"an":[145],"approach":[146],"phase-independent":[149],"iterative":[150],"spectrogram":[151],"inversion":[152],"employed":[154],"adaptation.":[157,196],"Significant":[158],"reductions":[159],"errors":[161],"noted":[163],"adapting":[165],"speaking-rates.":[167],"combining":[172,190],"with":[175,194],"length":[177],"normalization":[178],"scaling":[181],"also":[183],"studied.":[184],"Additive":[185],"improvements":[186],"obtained":[188],"techniques":[193]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
