{"id":"https://openalex.org/W2103860014","doi":"https://doi.org/10.1186/1687-4722-2014-4","title":"Integrated exemplar-based template matching and statistical modeling for continuous speech recognition","display_name":"Integrated exemplar-based template matching and statistical modeling for continuous speech recognition","publication_year":2014,"publication_date":"2014-02-01","ids":{"openalex":"https://openalex.org/W2103860014","doi":"https://doi.org/10.1186/1687-4722-2014-4","mag":"2103860014"},"language":"en","primary_location":{"id":"doi:10.1186/1687-4722-2014-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2014-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2014-4","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2014-4","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070689721","display_name":"Xie Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xie Sun","raw_affiliation_strings":["Nuance Communications, Inc, 1 Wayside Rd, Burlington, MA, 01801, USA","Nuance Communications Inc., Burlington, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications, Inc, 1 Wayside Rd, Burlington, MA, 01801, USA","institution_ids":["https://openalex.org/I4210125787"]},{"raw_affiliation_string":"Nuance Communications Inc., Burlington, USA","institution_ids":["https://openalex.org/I4210125787"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033518479","display_name":"Yunxin Zhao","orcid":"https://orcid.org/0000-0001-5511-3692"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yunxin Zhao","raw_affiliation_strings":["Department of Computer Science, University of Missouri, Columbia, MO, 65211, USA","Department of Computer Science , University of Missouri, Columbia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Missouri, Columbia, MO, 65211, USA","institution_ids":["https://openalex.org/I76835614"]},{"raw_affiliation_string":"Department of Computer Science , University of Missouri, Columbia, USA","institution_ids":["https://openalex.org/I76835614"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5033518479"],"corresponding_institution_ids":["https://openalex.org/I76835614"],"apc_list":{"value":1635,"currency":"USD","value_usd":1635},"apc_paid":{"value":1635,"currency":"USD","value_usd":1635},"fwci":0.9697,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.85009735,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"2014","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9987999796867371,"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":0.9979000091552734,"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":0.7842220664024353},{"id":"https://openalex.org/keywords/template-matching","display_name":"Template matching","score":0.6645396947860718},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6432669162750244},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.570677638053894},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5549522042274475},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5400124192237854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5371070504188538},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5304911136627197},{"id":"https://openalex.org/keywords/template","display_name":"Template","score":0.425345778465271},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.41397565603256226}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7842220664024353},{"id":"https://openalex.org/C158096908","wikidata":"https://www.wikidata.org/wiki/Q3983303","display_name":"Template matching","level":3,"score":0.6645396947860718},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6432669162750244},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.570677638053894},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5549522042274475},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5400124192237854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5371070504188538},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5304911136627197},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.425345778465271},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.41397565603256226},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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:10.1186/1687-4722-2014-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2014-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2014-4","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1186/1687-4722-2014-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2014-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2014-4","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2103860014.pdf","grobid_xml":"https://content.openalex.org/works/W2103860014.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W40249630","https://openalex.org/W75173072","https://openalex.org/W88081813","https://openalex.org/W125657975","https://openalex.org/W136723611","https://openalex.org/W139267174","https://openalex.org/W157668738","https://openalex.org/W605575788","https://openalex.org/W939280201","https://openalex.org/W1490760466","https://openalex.org/W1560013842","https://openalex.org/W1993882792","https://openalex.org/W1994396704","https://openalex.org/W2023952145","https://openalex.org/W2033178790","https://openalex.org/W2046800867","https://openalex.org/W2077804127","https://openalex.org/W2083393647","https://openalex.org/W2097207027","https://openalex.org/W2099415988","https://openalex.org/W2102552546","https://openalex.org/W2103248292","https://openalex.org/W2111732304","https://openalex.org/W2112739286","https://openalex.org/W2117459613","https://openalex.org/W2117809880","https://openalex.org/W2118587967","https://openalex.org/W2119549281","https://openalex.org/W2126203737","https://openalex.org/W2126336864","https://openalex.org/W2131033001","https://openalex.org/W2134401616","https://openalex.org/W2143203634","https://openalex.org/W2158717203","https://openalex.org/W2160306971","https://openalex.org/W2171019095","https://openalex.org/W2401742515","https://openalex.org/W2407066106","https://openalex.org/W2407201230","https://openalex.org/W2598222894","https://openalex.org/W2603454388","https://openalex.org/W2609944322","https://openalex.org/W2799061466","https://openalex.org/W2805889152","https://openalex.org/W2915722758","https://openalex.org/W3143835353","https://openalex.org/W4243044416","https://openalex.org/W4247379750","https://openalex.org/W4255583213"],"related_works":["https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2136763963","https://openalex.org/W2361315595","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W2602219756","https://openalex.org/W1909151225","https://openalex.org/W3184123547","https://openalex.org/W2160030256"],"abstract_inverted_index":{"We":[0,18,45,93],"propose":[1,76,95],"a":[2,105,132],"novel":[3],"approach":[4,147],"of":[5,42,118,140,148,239],"integrating":[6,149],"exemplar-based":[7],"template":[8,21,64,80,84,90,101,121,150,173,216,230],"matching":[9,151],"with":[10,152],"statistical":[11,153],"modeling":[12,154,163],"to":[13,23,38,68,96],"improve":[14],"continuous":[15,135],"speech":[16,43,136],"recognition.":[17],"choose":[19],"the":[20,99,111,116,119,126,145,160,182,188,201,209,225,234],"unit":[22],"be":[24],"context-dependent":[25],"phone":[26,128],"segments":[27],"(triphone":[28],"context)":[29],"and":[30,55,71,87,131,169,190,215,229],"use":[31],"multiple":[32],"Gaussian":[33],"mixture":[34],"model":[35],"(GMM)":[36],"indices":[37],"represent":[39,115],"each":[40],"frame":[41],"templates.":[44],"investigate":[46],"two":[47,77],"different":[48],"local":[49,203,211,219,227],"distances,":[50],"log":[51],"likelihood":[52,89],"ratio":[53],"(LLR)":[54],"Kullback-Leibler":[56],"(KL)":[57],"divergence,":[58],"for":[59,79,166],"dynamic":[60],"time":[61],"warping":[62],"(DTW)-based":[63],"matching.":[65],"In":[66],"order":[67],"reduce":[69],"computation":[70,189],"storage":[72,191],"complexities,":[73],"we":[74],"also":[75,176],"methods":[78,175],"selection:":[81],"minimum":[82],"distance":[83,204,220],"selection":[85,91,174],"(MDTS)":[86],"maximum":[88],"(MLTS).":[92],"further":[94,232],"fine":[97],"tune":[98],"MLTS":[100,214,240],"representatives":[102],"by":[103],"using":[104,200],"GMM":[106],"merging":[107],"algorithm":[108],"so":[109],"that":[110,144],"GMMs":[112],"can":[113],"better":[114,206,222],"frames":[117],"selected":[120],"representatives.":[122],"Experimental":[123],"results":[124],"on":[125,237],"TIMIT":[127,168],"recognition":[129,137,157,235],"task":[130,139],"large":[133],"vocabulary":[134],"(LVCSR)":[138],"telehealth":[141,170],"captioning":[142],"demonstrated":[143],"proposed":[146],"significantly":[155],"improved":[156,233],"accuracy":[158,179,236],"over":[159,181],"hidden":[161],"Markov":[162],"(HMM)":[164],"baselines":[165],"both":[167],"tasks.":[171],"The":[172],"provided":[177],"significant":[178],"gains":[180],"HMM":[183],"baseline":[184],"while":[185,241],"largely":[186],"reducing":[187],"complexities.":[192],"When":[193],"all":[194],"templates":[195],"or":[196],"MDTS":[197],"were":[198],"used,":[199],"LLR":[202,226],"gave":[205,221],"performance":[207,223],"than":[208,224],"KL":[210,218],"distance.":[212],"For":[213],"compression,":[217],"distance,":[228],"compression":[231],"top":[238],"having":[242],"less":[243],"computational":[244],"cost.":[245]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}