{"id":"https://openalex.org/W2104634847","doi":"https://doi.org/10.1109/asru.2009.5373389","title":"Kernel metric learning for phonetic classification","display_name":"Kernel metric learning for phonetic classification","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2104634847","doi":"https://doi.org/10.1109/asru.2009.5373389","mag":"2104634847"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2009.5373389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373389","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/A5045413298","display_name":"Jui-Ting Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jui-Ting Huang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, US","Beckman Institute, University of Illinois at Urbana-Champaign 61801, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, US","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Beckman Institute, University of Illinois at Urbana-Champaign 61801, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100602872","display_name":"Xi Zhou","orcid":"https://orcid.org/0000-0003-2917-0436"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xi Zhou","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, US","Beckman Institute, University of Illinois at Urbana-Champaign 61801, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, US","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Beckman Institute, University of Illinois at Urbana-Champaign 61801, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, US","Beckman Institute, University of Illinois at Urbana-Champaign 61801, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, US","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Beckman Institute, University of Illinois at Urbana-Champaign 61801, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101457342","display_name":"Thomas S. Huang","orcid":"https://orcid.org/0000-0001-8474-5859"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Huang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, US","Beckman Institute, University of Illinois at Urbana-Champaign 61801, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, US","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Beckman Institute, University of Illinois at Urbana-Champaign 61801, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5045413298"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.11820354,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"141","last_page":"145"},"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":0.9997000098228455,"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":0.9994999766349792,"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/margin","display_name":"Margin (machine learning)","score":0.8159877061843872},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7596701979637146},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6873103380203247},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6539243459701538},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5509960055351257},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5447784662246704},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.5399870872497559},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.49352967739105225},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4925861954689026},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4849843978881836},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.4466455578804016},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32928135991096497},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32630813121795654},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.20326095819473267},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13621163368225098}],"concepts":[{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.8159877061843872},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7596701979637146},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6873103380203247},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6539243459701538},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5509960055351257},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5447784662246704},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.5399870872497559},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.49352967739105225},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4925861954689026},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4849843978881836},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4466455578804016},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32928135991096497},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32630813121795654},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.20326095819473267},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13621163368225098},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru.2009.5373389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373389","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.159.1221","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.159.1221","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.isle.uiuc.edu/pubs/2009/huang09asru.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.41999998688697815}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W30596880","https://openalex.org/W163345699","https://openalex.org/W2001496355","https://openalex.org/W2041823554","https://openalex.org/W2129156852","https://openalex.org/W2136609641","https://openalex.org/W2144760012","https://openalex.org/W2619993508","https://openalex.org/W2798766386","https://openalex.org/W4254313632","https://openalex.org/W6601201855","https://openalex.org/W7011231051"],"related_works":["https://openalex.org/W80423236","https://openalex.org/W3164669818","https://openalex.org/W1573546415","https://openalex.org/W2906993205","https://openalex.org/W2071572975","https://openalex.org/W2619993508","https://openalex.org/W2997457842","https://openalex.org/W1997431798","https://openalex.org/W36113703","https://openalex.org/W2038050265"],"abstract_inverted_index":{"While":[0],"a":[1,7,31,53,63,70,124],"sound":[2],"spoken":[3],"is":[4,99],"described":[5],"by":[6,52,88],"handful":[8],"of":[9,49,108,119,137],"frame-level":[10],"spectral":[11],"vectors,":[12],"not":[13],"all":[14],"frames":[15,39,51],"have":[16],"equal":[17],"contribution":[18],"for":[19],"either":[20],"human":[21],"perception":[22],"or":[23],"machine":[24],"classification.":[25],"In":[26],"this":[27],"paper,":[28],"we":[29],"introduce":[30],"novel":[32],"framework":[33],"to":[34,41,61,72,83,101,115],"automatically":[35],"emphasize":[36],"important":[37],"speech":[38,50,127],"relevant":[40],"phonetic":[42],"information.":[43],"We":[44],"jointly":[45],"learn":[46],"the":[47,57,67,81,89,103,135],"importance":[48],"distance":[54,68,82],"metric":[55],"across":[56],"phone":[58,86,109,121],"classes,":[59],"attempting":[60],"satisfy":[62],"large":[64,125],"margin":[65,126],"constraint:":[66],"from":[69],"segment":[71],"its":[73],"correct":[74],"label":[75],"class":[76,87],"should":[77],"be":[78],"less":[79],"than":[80],"any":[84],"other":[85],"largest":[90],"possible":[91],"margin.":[92],"Furthermore,":[93],"an":[94],"universal":[95],"background":[96],"model":[97],"structure":[98],"proposed":[100],"give":[102],"correspondence":[104],"between":[105],"statistical":[106,117],"models":[107,118],"types":[110],"and":[111],"tokens,":[112],"allowing":[113],"us":[114],"use":[116],"each":[120],"token":[122],"in":[123],"recognition":[128],"framework.":[129,139],"Experiments":[130],"on":[131],"TIMIT":[132],"database":[133],"demonstrated":[134],"effectiveness":[136],"our":[138]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}