{"id":"https://openalex.org/W3160257947","doi":"https://doi.org/10.1109/icassp39728.2021.9413442","title":"A Stage Match for Query-by-Example Spoken Term Detection Based On Structure Information of Query","display_name":"A Stage Match for Query-by-Example Spoken Term Detection Based On Structure Information of Query","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160257947","doi":"https://doi.org/10.1109/icassp39728.2021.9413442","mag":"3160257947"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5023493888","display_name":"Junyao Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junyao Zhan","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102706072","display_name":"Qianhua He","orcid":"https://orcid.org/0000-0002-9079-4566"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianhua He","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102398562","display_name":"Jianbin Su","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianbin Su","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070863631","display_name":"Yanxiong Li","orcid":"https://orcid.org/0000-0003-4362-1125"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanxiong Li","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5023493888"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":0.42,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.68332413,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6833","last_page":"6837"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9962000250816345,"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":0.9896000027656555,"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/dynamic-time-warping","display_name":"Dynamic time warping","score":0.8940064907073975},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8092972040176392},{"id":"https://openalex.org/keywords/query-by-example","display_name":"Query by Example","score":0.7875950932502747},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5479989051818848},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.5313926935195923},{"id":"https://openalex.org/keywords/sliding-window-protocol","display_name":"Sliding window protocol","score":0.5234476923942566},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.5017204284667969},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47820591926574707},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42987245321273804},{"id":"https://openalex.org/keywords/sargable","display_name":"Sargable","score":0.4196653962135315},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4182095527648926},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3851427137851715},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.3593944311141968},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.26998430490493774},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.23168176412582397},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.20121845602989197},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09019190073013306}],"concepts":[{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.8940064907073975},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8092972040176392},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.7875950932502747},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5479989051818848},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.5313926935195923},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.5234476923942566},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.5017204284667969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47820591926574707},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42987245321273804},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.4196653962135315},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4182095527648926},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3851427137851715},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.3593944311141968},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.26998430490493774},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.23168176412582397},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.20121845602989197},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09019190073013306},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1496120315","https://openalex.org/W1985809919","https://openalex.org/W1998766338","https://openalex.org/W2041305643","https://openalex.org/W2046955072","https://openalex.org/W2114347655","https://openalex.org/W2115101691","https://openalex.org/W2129075707","https://openalex.org/W2137044559","https://openalex.org/W2137089646","https://openalex.org/W2152051032","https://openalex.org/W2155513114","https://openalex.org/W2338585947","https://openalex.org/W2889270419","https://openalex.org/W2962736743","https://openalex.org/W2963242190","https://openalex.org/W2963624290","https://openalex.org/W2971021568","https://openalex.org/W2972764223","https://openalex.org/W3015210390"],"related_works":["https://openalex.org/W3081572596","https://openalex.org/W1530001627","https://openalex.org/W2392467230","https://openalex.org/W1507688934","https://openalex.org/W3118696700","https://openalex.org/W1541456318","https://openalex.org/W2354970673","https://openalex.org/W988193086","https://openalex.org/W2388669825","https://openalex.org/W3160257947"],"abstract_inverted_index":{"The":[0,81],"state-of-the-art":[1],"of":[2,27,52,68,76,112,118,138],"query-by-example":[3],"spoken":[4],"term":[5],"detection":[6],"(QbE-STD)":[7],"strategies":[8],"are":[9],"usually":[10],"based":[11,63],"on":[12,64,126],"segmental":[13],"dynamic":[14],"time":[15],"warping":[16],"(S-DTW).":[17],"However,":[18],"the":[19,43,48,65,69,73,77,91,98,110,122,131,147],"sliding":[20],"window":[21],"in":[22,79,93,121,140],"S-DTW":[23,143],"may":[24],"separate":[25],"signal":[26],"a":[28,59,106,135],"word":[29],"into":[30],"different":[31],"segments":[32],"and":[33,50,95,115,144],"produce":[34],"many":[35],"illegal":[36],"candidates":[37,86],"required":[38],"to":[39],"be":[40],"compared":[41],"with":[42,72,87,100,109],"query,":[44,70],"which":[45,104],"significantly":[46],"reduce":[47],"accuracy":[49],"efficiency":[51],"detection.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57],"propose":[58],"stage":[60],"match":[61],"strategy":[62,82],"structure":[66,89],"information":[67],"represented":[71],"unvoiced-voiced":[74],"attribute":[75],"portions":[78],"itself.":[80],"first":[83],"locates":[84],"potential":[85],"similar":[88],"against":[90,142],"query":[92,99],"utterances,":[94],"further":[96],"matches":[97],"Type-Location":[101],"DTW":[102,108],"(TL-DTW),":[103],"is":[105],"modified":[107],"constraints":[111],"pronunciation":[113],"types":[114],"relative":[116,136],"positions":[117],"paired":[119],"frames":[120],"voiced":[123],"sub-segments.":[124],"Experiments":[125],"AISHELL-1":[127],"Corpus":[128],"showed":[129],"that":[130],"proposed":[132],"approach":[133],"achieved":[134],"improvement":[137],"30.51%":[139],"AUC":[141],"speeded":[145],"up":[146],"retrieval.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
