{"id":"https://openalex.org/W1513860483","doi":"https://doi.org/10.1109/icassp.2015.7178956","title":"Exemplar-based large vocabulary speech recognition using k-nearest neighbors","display_name":"Exemplar-based large vocabulary speech recognition using k-nearest neighbors","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1513860483","doi":"https://doi.org/10.1109/icassp.2015.7178956","mag":"1513860483"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178956","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178956","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5036374289","display_name":"Yanbo Xu","orcid":"https://orcid.org/0000-0003-4129-7376"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yanbo Xu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Maryland, College Park, MD, USA","Google, NYC"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"Google, NYC","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005881531","display_name":"Olivier Siohan","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Olivier Siohan","raw_affiliation_strings":["Google Inc., New York"],"affiliations":[{"raw_affiliation_string":"Google Inc., New York","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016220938","display_name":"David Simcha","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Simcha","raw_affiliation_strings":["Google Inc., New York"],"affiliations":[{"raw_affiliation_string":"Google Inc., New York","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018301052","display_name":"Sanjiv Kumar","orcid":"https://orcid.org/0000-0002-4080-1414"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjiv Kumar","raw_affiliation_strings":["Google Inc., New York"],"affiliations":[{"raw_affiliation_string":"Google Inc., New York","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110698977","display_name":"Hank Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hank Liao","raw_affiliation_strings":["Google Inc., New York"],"affiliations":[{"raw_affiliation_string":"Google Inc., New York","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5036374289"],"corresponding_institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":0.8932,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.81896917,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5167","last_page":"5171"},"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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.7916339635848999},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6336562633514404},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5800577402114868},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.540444016456604},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5319293737411499},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5155739188194275},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.5116181969642639},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5076545476913452},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4661701023578644},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.46247756481170654},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.45582422614097595},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.44674551486968994},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4417983591556549},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.4350413382053375},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4279686212539673},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.41905882954597473}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7916339635848999},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6336562633514404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5800577402114868},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.540444016456604},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5319293737411499},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5155739188194275},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.5116181969642639},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5076545476913452},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4661701023578644},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.46247756481170654},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45582422614097595},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.44674551486968994},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4417983591556549},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.4350413382053375},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4279686212539673},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.41905882954597473},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7178956","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178956","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6899999976158142,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W38854004","https://openalex.org/W156258841","https://openalex.org/W1571002681","https://openalex.org/W1634005169","https://openalex.org/W1734538896","https://openalex.org/W1877570817","https://openalex.org/W1970663544","https://openalex.org/W2023952145","https://openalex.org/W2033256038","https://openalex.org/W2058641082","https://openalex.org/W2075925017","https://openalex.org/W2109664771","https://openalex.org/W2114853176","https://openalex.org/W2116429588","https://openalex.org/W2122111042","https://openalex.org/W2124509324","https://openalex.org/W2168231600","https://openalex.org/W2173213060","https://openalex.org/W2189391786","https://openalex.org/W2294962864","https://openalex.org/W2308899597","https://openalex.org/W6601575315","https://openalex.org/W6634097936","https://openalex.org/W6687284999","https://openalex.org/W6697031438","https://openalex.org/W6698220937"],"related_works":["https://openalex.org/W2364370872","https://openalex.org/W2097963413","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W3145575561","https://openalex.org/W2995886640","https://openalex.org/W1591475660","https://openalex.org/W2001275470","https://openalex.org/W2164162849","https://openalex.org/W2914064142"],"abstract_inverted_index":{"This":[0,63],"paper":[1],"describes":[2],"a":[3,33,49,52,130],"large":[4,11],"scale":[5],"exemplar-based":[6],"acoustic":[7],"modeling":[8],"approach":[9,102],"for":[10,94],"vocabulary":[12],"continuous":[13],"speech":[14],"recognition.":[15,95],"We":[16,121],"construct":[17,111],"an":[18,79,97,112],"index":[19,113],"of":[20,32,54,81,86,118],"labeled":[21],"training":[22,119],"frames":[23,57,74],"using":[24,68],"high-level":[25],"features":[26],"extracted":[27],"from":[28,60],"the":[29,61,72,82,87],"bottleneck":[30],"layer":[31],"deep":[34],"neural":[35],"network":[36],"as":[37],"indexing":[38],"features.":[39],"At":[40],"recognition":[41,127],"time,":[42],"each":[43],"test":[44],"frame":[45,124],"is":[46,58,65],"turned":[47],"into":[48],"query":[50],"and":[51,71,126],"set":[53,64],"k-nearest":[55],"neighbor":[56,100],"retrieved":[59],"index.":[62],"further":[66],"filtered":[67],"majority":[69],"voting":[70],"remaining":[73],"are":[75,108],"used":[76,93],"to":[77,110],"derive":[78],"estimate":[80],"context-dependent":[83],"state":[84],"posteriors":[85],"query,":[88],"which":[89],"can":[90],"then":[91],"be":[92],"Using":[96],"approximate":[98],"nearest":[99],"search":[101],"based":[103],"on":[104,114,129],"asymmetric":[105],"hashing,":[106],"we":[107],"able":[109],"over":[115],"25,000":[116],"hours":[117],"data.":[120],"present":[122],"both":[123],"classification":[125],"experiments":[128],"Voice":[131],"Search":[132],"task.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}