{"id":"https://openalex.org/W1983300351","doi":"https://doi.org/10.1109/icassp.2013.6639334","title":"Toward unsupervised model-based spoken term detection with spoken queries without annotated data","display_name":"Toward unsupervised model-based spoken term detection with spoken queries without annotated data","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W1983300351","doi":"https://doi.org/10.1109/icassp.2013.6639334","mag":"1983300351"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5105193799","display_name":"Chun-an Chan","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chun-an Chan","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taiwan","[Grad. Inst. of Commun. Eng., Nat. Taiwan Univ., Taipei, Taiwan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"[Grad. Inst. of Commun. Eng., Nat. Taiwan Univ., Taipei, Taiwan]","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102330488","display_name":"Cheng-Tao Chung","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng-Tao Chung","raw_affiliation_strings":["Graduate Institute of Electrical Engineering, National Taiwan University, Taiwan","Grad. Inst. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Electrical Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Grad. Inst. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102964085","display_name":"Yu\u2010Hsin Kuo","orcid":"https://orcid.org/0000-0003-0239-1941"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Hsin Kuo","raw_affiliation_strings":["Department of Electrical Engineering, National Taiwan University, Taiwan","Dept. of Electr. Eng.. Nat. Taiwan Univ., Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Dept. of Electr. Eng.. Nat. Taiwan Univ., Taipei, Taiwan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044010123","display_name":"Lin-shan Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Lin-shan Lee","raw_affiliation_strings":["Graduate Institute of Communication Engineering, Graduate Institute of Electrical Engineering,, National Taiwan University, Taiwan","[Grad. Inst. of Commun. Eng., Nat. Taiwan Univ., Taipei, Taiwan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, Graduate Institute of Electrical Engineering,, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"[Grad. Inst. of Commun. Eng., Nat. Taiwan Univ., Taipei, Taiwan]","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":1.6017,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.8426048,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"9","issue":null,"first_page":"8550","last_page":"8554"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9962999820709229,"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/T12031","display_name":"Speech and dialogue systems","score":0.9936000108718872,"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/computer-science","display_name":"Computer science","score":0.8173035383224487},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6288228034973145},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.5992780923843384},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5782535076141357},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5478172898292542},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5221576690673828},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4934748411178589},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.4561734199523926},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.43691083788871765},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42784303426742554},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33582252264022827},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07255628705024719},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07103309035301208}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8173035383224487},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6288228034973145},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.5992780923843384},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5782535076141357},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5478172898292542},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5221576690673828},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4934748411178589},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.4561734199523926},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.43691083788871765},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42784303426742554},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33582252264022827},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07255628705024719},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07103309035301208},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6639334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1815792","https://openalex.org/W36723659","https://openalex.org/W49437105","https://openalex.org/W77404731","https://openalex.org/W114193738","https://openalex.org/W1534656595","https://openalex.org/W2015688877","https://openalex.org/W2083393647","https://openalex.org/W2096298528","https://openalex.org/W2109173967","https://openalex.org/W2110589736","https://openalex.org/W2110625382","https://openalex.org/W2111942273","https://openalex.org/W2116422968","https://openalex.org/W2121742134","https://openalex.org/W2126203737","https://openalex.org/W2164365067","https://openalex.org/W2164512012","https://openalex.org/W2170659185","https://openalex.org/W2171019095","https://openalex.org/W2293210169","https://openalex.org/W2403642609","https://openalex.org/W2407151108","https://openalex.org/W2407964052","https://openalex.org/W2612891210","https://openalex.org/W6602023532","https://openalex.org/W6604666349","https://openalex.org/W6608351678"],"related_works":["https://openalex.org/W2419138286","https://openalex.org/W2136652457","https://openalex.org/W2507549656","https://openalex.org/W2050318184","https://openalex.org/W101156158","https://openalex.org/W2182848507","https://openalex.org/W2169849734","https://openalex.org/W2387825067","https://openalex.org/W2116722627","https://openalex.org/W2506414444"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,45,92,115,175,190],"two-stage":[3],"model-based":[4,31],"approach":[5,188],"for":[6,23,108],"unsupervised":[7,25,80],"query-by-example":[8],"spoken":[9,51,67,84,110,149],"term":[10,150],"detection":[11],"(STD)":[12],"without":[13],"any":[14],"annotated":[15],"data.":[16],"Compared":[17],"to":[18,103,123,144,159,184],"the":[19,24,36,50,60,66,83,87,104,109,130,138,156,185],"prevailing":[20],"DTW":[21,187],"approaches":[22,32],"STD":[26],"task,":[27],"HMMs":[28],"used":[29,143],"by":[30],"can":[33],"better":[34],"capture":[35],"signal":[37],"distributions":[38],"and":[39],"time":[40,182],"trajectories":[41],"of":[42,49,169],"speech":[43],"with":[44,54,155,174],"more":[46,176],"global":[47],"view":[48],"archive;":[52],"matching":[53,95],"model":[55],"states":[56],"also":[57],"significantly":[58],"reduces":[59],"computational":[61],"load.":[62],"The":[63],"utterances":[64],"in":[65,78,180],"archive":[68],"are":[69,101,141],"first":[70,88,139],"offline":[71],"decoded":[72],"into":[73],"acoustic":[74],"patterns":[75],"automatically":[76],"discovered":[77],"an":[79,166],"way":[81],"from":[82,137],"archive.":[85],"In":[86,112,129],"stage,":[89,132],"we":[90],"propose":[91],"document":[93],"state":[94,106],"(DSM)":[96],"approach,":[97],"where":[98],"query":[99],"frames":[100],"matched":[102],"HMM":[105],"sequences":[107],"documents.":[111],"this":[113],"process,":[114],"novel":[116],"duration-constrained":[117],"Viterbi":[118],"(DC-Vite)":[119],"algorithm":[120],"is":[121,152],"proposed":[122],"avoid":[124],"unrealistic":[125],"speaking":[126],"rate":[127],"distortion.":[128],"second":[131],"pseudo":[133],"relevant/irrelevant":[134],"examples":[135],"retrieved":[136],"stage":[140],"respectively":[142],"construct":[145],"query/anti-query":[146],"HMMs.":[147,162],"Each":[148],"hypothesis":[151],"then":[153],"rescored":[154],"likelihood":[157],"ratio":[158],"these":[160],"two":[161],"Experimental":[163],"results":[164],"show":[165],"absolute":[167],"11.8%":[168],"mean":[170],"average":[171],"precision":[172],"improvement":[173],"than":[177],"50%":[178],"reduction":[179],"computation":[181],"compared":[183],"segmental":[186],"on":[189],"Mandarin":[191],"broadcast":[192],"news":[193],"corpus.":[194]},"counts_by_year":[{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}