{"id":"https://openalex.org/W1983042831","doi":"https://doi.org/10.1109/tasl.2013.2248714","title":"Model-Based Unsupervised Spoken Term Detection with Spoken Queries","display_name":"Model-Based Unsupervised Spoken Term Detection with Spoken Queries","publication_year":2013,"publication_date":"2013-02-23","ids":{"openalex":"https://openalex.org/W1983042831","doi":"https://doi.org/10.1109/tasl.2013.2248714","mag":"1983042831"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2013.2248714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2013.2248714","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/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, Taipei, 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, Taipei, 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":"last","author":{"id":"https://openalex.org/A5113499149","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, National Taiwan University, Taipei, 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, Taipei, 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":5.3545,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.95253724,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"21","issue":"7","first_page":"1330","last_page":"1342"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9987000226974487,"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":0.9951000213623047,"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":0.8223806023597717},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5858168005943298},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5572079420089722},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5544690489768982},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.5335828065872192},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.4793299436569214},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.4742649793624878},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4720103442668915},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46724796295166016},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40276989340782166},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3994693458080292}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8223806023597717},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5858168005943298},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5572079420089722},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5544690489768982},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.5335828065872192},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.4793299436569214},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.4742649793624878},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4720103442668915},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46724796295166016},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40276989340782166},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3994693458080292},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2013.2248714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2013.2248714","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1815792","https://openalex.org/W30596880","https://openalex.org/W36723659","https://openalex.org/W49437105","https://openalex.org/W51277926","https://openalex.org/W77404731","https://openalex.org/W79749824","https://openalex.org/W114193738","https://openalex.org/W131856359","https://openalex.org/W161183367","https://openalex.org/W1488355515","https://openalex.org/W1490960657","https://openalex.org/W1534656595","https://openalex.org/W1606311031","https://openalex.org/W1957665339","https://openalex.org/W1990227353","https://openalex.org/W2015688877","https://openalex.org/W2083393647","https://openalex.org/W2094753663","https://openalex.org/W2099415988","https://openalex.org/W2100768664","https://openalex.org/W2103933358","https://openalex.org/W2106284094","https://openalex.org/W2109173967","https://openalex.org/W2110589736","https://openalex.org/W2110625382","https://openalex.org/W2111942273","https://openalex.org/W2114347655","https://openalex.org/W2120477910","https://openalex.org/W2121742134","https://openalex.org/W2121997342","https://openalex.org/W2126203737","https://openalex.org/W2128160875","https://openalex.org/W2133184712","https://openalex.org/W2139106564","https://openalex.org/W2164365067","https://openalex.org/W2164512012","https://openalex.org/W2169347997","https://openalex.org/W2170659185","https://openalex.org/W2171019095","https://openalex.org/W2293210169","https://openalex.org/W2399869768","https://openalex.org/W2403207842","https://openalex.org/W2403642609","https://openalex.org/W2407151108","https://openalex.org/W2442329935","https://openalex.org/W2612891210","https://openalex.org/W4235963273","https://openalex.org/W6602023532","https://openalex.org/W6603191899","https://openalex.org/W6606613475","https://openalex.org/W6629386585","https://openalex.org/W6640828828","https://openalex.org/W6675022971","https://openalex.org/W6677803786","https://openalex.org/W6684724424","https://openalex.org/W6718561954"],"related_works":["https://openalex.org/W2419138286","https://openalex.org/W2136652457","https://openalex.org/W2507549656","https://openalex.org/W2050318184","https://openalex.org/W2182848507","https://openalex.org/W2169849734","https://openalex.org/W2387825067","https://openalex.org/W2116722627","https://openalex.org/W2506414444","https://openalex.org/W2129150969"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,74,126,157,258],"set":[3],"of":[4,43,111,117,199,209,241],"model-based":[5,34],"approaches":[6,35,226],"for":[7,36,121,140,201],"unsupervised":[8,37],"spoken":[9,14,190],"term":[10,191],"detection":[11],"(STD)":[12],"with":[13,176,180,246,252],"queries":[15],"that":[16],"requires":[17],"neither":[18],"speech":[19],"recognition":[20],"nor":[21],"annotated":[22],"data.":[23],"This":[24],"work":[25],"shows":[26],"the":[27,55,70,92,101,105,114,122,141,147,153,166,188,197,207,228,232,253],"possibilities":[28],"in":[29,165,203,231],"migrating":[30],"from":[31],"DTW-based":[32,225],"to":[33,82,91,125,145,186],"STD.":[38],"The":[39,193,218],"proposed":[40,81,139,164,194,233],"approach":[41,79,162,256],"consists":[42],"three":[44],"components:":[45],"self-organizing":[46,56],"models,":[47,57],"query":[48,51,71,93,154],"matching,":[49],"and":[50,62,108,206,269],"modeling.":[52],"To":[53],"construct":[54],"repeated":[58],"patterns":[59],"are":[60,89],"captured":[61],"modeled":[63],"using":[64,215],"acoustic":[65],"segment":[66],"models":[67],"(ASMs).":[68],"In":[69,95,152],"matching":[72,77,143],"phase,":[73,156],"document":[75],"state":[76],"(DSM)":[78],"is":[80,137,163,184,221],"represent":[83],"documents":[84,123],"as":[85],"ASM":[86,216],"sequences,":[87],"which":[88],"matched":[90],"frames.":[94],"this":[96],"way,":[97],"not":[98],"only":[99],"do":[100],"ASMs":[102,200],"better":[103],"model":[104],"signal":[106],"distributions":[107],"time":[109,249],"trajectories":[110],"speech,":[112],"but":[113],"much-smaller":[115],"number":[116],"states":[118],"than":[119],"frames":[120],"leads":[124],"much":[127],"lower":[128],"computational":[129],"load.":[130],"A":[131,172],"novel":[132],"duration-constrained":[133],"Viterbi":[134],"(DC-Vite)":[135],"algorithm":[136],"further":[138],"above":[142],"process":[144],"handle":[146],"speaking":[148],"rate":[149],"distortion":[150],"problem.":[151],"modeling":[155],"pseudo":[158,167,181],"likelihood":[159,173],"ratio":[160,174],"(PLR)":[161],"relevance":[168],"feedback":[169],"(PRF)":[170],"framework.":[171,234],"evaluated":[175],"query/anti-query":[177],"HMMs":[178],"trained":[179],"relevant/irrelevant":[182],"examples":[183],"used":[185],"verify":[187],"detected":[189],"hypotheses.":[192],"framework":[195],"demonstrates":[196],"usefulness":[198],"STD":[202,213],"zero-resource":[204],"settings":[205],"potential":[208],"an":[210,238],"instantly":[211],"responding":[212],"system":[214],"indexing.":[217],"best":[219],"performance":[220],"achieved":[222],"by":[223],"integrating":[224],"into":[227],"rescoring":[229],"steps":[230],"Experimental":[235],"results":[236],"show":[237],"absolute":[239],"14.2%":[240],"mean":[242],"average":[243],"precision":[244],"improvement":[245],"77%":[247],"CPU":[248],"reduction":[250],"compared":[251],"segmental":[254],"DTW":[255],"on":[257,267],"Mandarin":[259],"broadcast":[260],"news":[261],"corpus.":[262,275],"Consistent":[263],"improvements":[264],"were":[265],"found":[266],"TIMIT":[268],"MediaEval":[270],"2011":[271],"Spoken":[272],"Web":[273],"Search":[274]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}