{"id":"https://openalex.org/W2397535009","doi":"https://doi.org/10.21437/interspeech.2011-620","title":"Nearest neighbors with learned distances for phonetic frame classification","display_name":"Nearest neighbors with learned distances for phonetic frame classification","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2397535009","doi":"https://doi.org/10.21437/interspeech.2011-620","mag":"2397535009"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-620","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","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/A5033965231","display_name":"John Labiak","orcid":null},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"John Labiak","raw_affiliation_strings":["University of Chicago (  )"],"affiliations":[{"raw_affiliation_string":"University of Chicago (  )","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015602781","display_name":"Karen Livescu","orcid":"https://orcid.org/0000-0003-4962-946X"},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karen Livescu","raw_affiliation_strings":["Toyota Technological Institute at Chicago,"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago,","institution_ids":["https://openalex.org/I160992636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5033965231"],"corresponding_institution_ids":["https://openalex.org/I40347166"],"apc_list":null,"apc_paid":null,"fwci":1.2472,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.81526052,"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":"2337","last_page":"2340"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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":0.9991999864578247,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9979000091552734,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/large-margin-nearest-neighbor","display_name":"Large margin nearest neighbor","score":0.8206185698509216},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.714095413684845},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.6779230833053589},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6374505162239075},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6347558498382568},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.6296402812004089},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.6022850275039673},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.5548831820487976},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.5458198189735413},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4644835889339447},{"id":"https://openalex.org/keywords/mahalanobis-distance","display_name":"Mahalanobis distance","score":0.46283960342407227},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4564213752746582},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4494282603263855},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4332748353481293},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.41594311594963074},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34269505739212036},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.21900328993797302},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.17806139588356018},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.11011230945587158}],"concepts":[{"id":"https://openalex.org/C94475309","wikidata":"https://www.wikidata.org/wiki/Q6489154","display_name":"Large margin nearest neighbor","level":3,"score":0.8206185698509216},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.714095413684845},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.6779230833053589},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6374505162239075},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6347558498382568},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.6296402812004089},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.6022850275039673},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.5548831820487976},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.5458198189735413},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4644835889339447},{"id":"https://openalex.org/C1921717","wikidata":"https://www.wikidata.org/wiki/Q1334846","display_name":"Mahalanobis distance","level":2,"score":0.46283960342407227},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4564213752746582},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4494282603263855},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4332748353481293},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.41594311594963074},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34269505739212036},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.21900328993797302},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.17806139588356018},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.11011230945587158},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2011-620","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.411.9565","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.411.9565","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ttic.uchicago.edu/~klivescu/papers/labiak_livescu_interspeech2011.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W38854004","https://openalex.org/W75173072","https://openalex.org/W1586283311","https://openalex.org/W2038276547","https://openalex.org/W2106053110","https://openalex.org/W2116429588","https://openalex.org/W2122111042","https://openalex.org/W2154872931","https://openalex.org/W2169351022"],"related_works":["https://openalex.org/W3094967175","https://openalex.org/W50423144","https://openalex.org/W3096071782","https://openalex.org/W2902799860","https://openalex.org/W4289129280","https://openalex.org/W2298736013","https://openalex.org/W2170605888","https://openalex.org/W2131929066","https://openalex.org/W2155982529","https://openalex.org/W3082824678"],"abstract_inverted_index":{"Nearest":[0],"neighbor-based":[1],"techniques":[2],"provide":[3],"an":[4],"approach":[5],"to":[6,47,73],"acoustic":[7],"modeling":[8],"that":[9,126],"avoids":[10],"the":[11,26,30,43,75,83,101,110,127],"often":[12],"lengthy":[13],"and":[14,58,96],"heuristic":[15],"process":[16],"of":[17,28,78,86,92,103,107],"training":[18],"traditional":[19],"Gaussian":[20,94,117],"mixturebased":[21],"models.":[22],"Here":[23],"we":[24],"study":[25],"problem":[27],"choosing":[29],"distance":[31,46,147],"metric":[32],"for":[33,68],"a":[34],"k-nearest":[35],"neighbor":[36,71],"(k-NN)":[37],"phonetic":[38,104],"frame":[39,105],"classifier.":[40],"We":[41,63,81,124],"compare":[42,82],"standard":[44],"Euclidean":[45],"two":[48],"learned":[49],"Mahalanobis":[50],"distances,":[51],"based":[52],"on":[53,100],"large-margin":[54],"nearest":[55,70,145],"neighbors":[56],"(LMNN)":[57],"locality":[59,65],"preserving":[60],"projections":[61],"(LPP).":[62],"use":[64],"sensitive":[66],"hashing":[67],"approximate":[69],"search":[72],"reduce":[74],"test":[76],"time":[77],"k-NN":[79,114,129],"classification.":[80],"error":[84],"rates":[85],"these":[87],"approaches,":[88],"as":[89,91],"well":[90],"baseline":[93],"mixture-based":[95],"multilayer":[97,122,149],"perceptron":[98],"classifiers,":[99],"task":[102],"classification":[106,130],"speech":[108],"from":[109],"TIMIT":[111],"database.":[112],"The":[113],"classifiers":[115],"outperform":[116],"mixture":[118],"models,":[119],"but":[120],"not":[121],"perceptrons.":[123],"find":[125],"best":[128],"performance":[131],"is":[132,138],"obtained":[133],"using":[134],"LPP,":[135],"while":[136],"LMNN":[137],"close":[139],"behind.":[140],"Index":[141],"Terms:":[142],"Phonetic":[143],"classification,":[144],"neighbors,":[146],"learning,":[148],"perceptrons":[150],"1.":[151]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}