{"id":"https://openalex.org/W2171670492","doi":"https://doi.org/10.1109/asru.2009.5373326","title":"Articulatory feature detection with Support Vector Machines for integration into ASR and phone recognition","display_name":"Articulatory feature detection with Support Vector Machines for integration into ASR and phone recognition","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2171670492","doi":"https://doi.org/10.1109/asru.2009.5373326","mag":"2171670492"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2009.5373326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","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/A5110218731","display_name":"Upendra V. Chaudhari","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Upendra V. Chaudhari","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034529775","display_name":"Michael Picheny","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Picheny","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5110218731"],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":1.3086,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.85490882,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"93","last_page":"98"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9980000257492065,"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":0.8063664436340332},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.779827356338501},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6899363994598389},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6675130724906921},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5959645509719849},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5905168056488037},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5899350643157959},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5656033754348755},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5258760452270508},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.48077625036239624},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4745907485485077},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.43234026432037354},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2928411364555359}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8063664436340332},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.779827356338501},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6899363994598389},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6675130724906921},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5959645509719849},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5905168056488037},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5899350643157959},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5656033754348755},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5258760452270508},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.48077625036239624},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4745907485485077},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.43234026432037354},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2928411364555359},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2009.5373326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W45736138","https://openalex.org/W234669733","https://openalex.org/W1559678887","https://openalex.org/W1618905105","https://openalex.org/W2003890417","https://openalex.org/W2053280194","https://openalex.org/W2074417845","https://openalex.org/W2097399990","https://openalex.org/W2116648050","https://openalex.org/W2125234026","https://openalex.org/W2125610823","https://openalex.org/W2147467930","https://openalex.org/W2148226542","https://openalex.org/W2165436104","https://openalex.org/W3119651796","https://openalex.org/W4285719527","https://openalex.org/W6633418959","https://openalex.org/W6633616865","https://openalex.org/W6636501900","https://openalex.org/W6678457041"],"related_works":["https://openalex.org/W2090763504","https://openalex.org/W148178222","https://openalex.org/W1948992892","https://openalex.org/W2104657898","https://openalex.org/W1886884218","https://openalex.org/W1910826599","https://openalex.org/W1980100242","https://openalex.org/W2530420969","https://openalex.org/W2101357962","https://openalex.org/W2785641460"],"abstract_inverted_index":{"We":[0,60],"study":[1],"the":[2,11,22,26,47,50,74,84,98,110],"use":[3],"of":[4,13,49,109],"support":[5],"vector":[6],"machines":[7],"(SVM)":[8],"for":[9,73],"detecting":[10],"occurrence":[12],"articulatory":[14],"features":[15],"in":[16,25,57,83],"speech":[17,33,112],"audio":[18],"data":[19,128],"and":[20,32,77],"using":[21,67,86],"information":[23],"contained":[24],"detector":[27,100],"outputs":[28,101],"to":[29,44,81],"improve":[30],"phone":[31],"recognition.":[34],"Our":[35],"expectation":[36],"is":[37],"that":[38,62,97],"an":[39],"SVM":[40,75],"should":[41],"be":[42,103],"able":[43],"appropriately":[45],"model":[46],"separation":[48],"classes":[51],"which":[52],"may":[53],"have":[54],"complex":[55],"distributions":[56],"feature":[58],"space.":[59],"show":[61,96],"performance":[63,117],"improves":[64],"markedly":[65],"when":[66],"discriminatively":[68],"trained":[69],"speaker":[70],"dependent":[71],"parameters":[72],"inputs,":[76],"compares":[78],"quite":[79],"well":[80],"results":[82],"literature":[85],"other":[87],"classifiers,":[88],"namely":[89],"artificial":[90],"neural":[91],"networks":[92],"(ANN).":[93],"Further,":[94],"we":[95,120],"resulting":[99],"can":[102],"successfully":[104],"integrated":[105],"into":[106],"a":[107],"state":[108],"art":[111],"recognition":[113],"system,":[114],"with":[115],"consequent":[116],"gains.":[118],"Notably,":[119],"test":[121],"our":[122],"system":[123],"on":[124],"English":[125],"broadcast":[126],"news":[127],"from":[129],"dev04f.":[130]},"counts_by_year":[{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}