{"id":"https://openalex.org/W4200203405","doi":"https://doi.org/10.1109/gcce53005.2021.9621804","title":"Robust Query-by-example Spoken Term Detection for Unknown Words Using Speech Retrieval-oriented E2E ASR Modeling","display_name":"Robust Query-by-example Spoken Term Detection for Unknown Words Using Speech Retrieval-oriented E2E ASR Modeling","publication_year":2021,"publication_date":"2021-10-12","ids":{"openalex":"https://openalex.org/W4200203405","doi":"https://doi.org/10.1109/gcce53005.2021.9621804"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce53005.2021.9621804","pdf_url":null,"source":{"id":"https://openalex.org/S4363607807","display_name":"2021 IEEE 10th Global Conference on Consumer Electronics (GCCE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5026439155","display_name":"Takumi Kurokawa","orcid":null},"institutions":[{"id":"https://openalex.org/I1298590031","display_name":"Shizuoka University","ror":"https://ror.org/01w6wtk13","country_code":"JP","type":"education","lineage":["https://openalex.org/I1298590031"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takumi Kurokawa","raw_affiliation_strings":["Graduate School of Science and Technology, Shizuoka University, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Technology, Shizuoka University, Japan","institution_ids":["https://openalex.org/I1298590031"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071123569","display_name":"Atsuhiko Kai","orcid":null},"institutions":[{"id":"https://openalex.org/I1298590031","display_name":"Shizuoka University","ror":"https://ror.org/01w6wtk13","country_code":"JP","type":"education","lineage":["https://openalex.org/I1298590031"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsuhiko Kai","raw_affiliation_strings":["Graduate School of Science and Technology, Shizuoka University, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Technology, Shizuoka University, Japan","institution_ids":["https://openalex.org/I1298590031"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":58},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition Technology","score":0.9994,"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 Technology","score":0.9994,"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 Enhancement Techniques","score":0.9828,"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":"Audio Signal Classification and Analysis","score":0.9825,"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/end-to-end-speech-recognition","display_name":"End-to-End Speech Recognition","score":0.611634},{"id":"https://openalex.org/keywords/audio-visual-speech-recognition","display_name":"Audio-Visual Speech Recognition","score":0.605095},{"id":"https://openalex.org/keywords/automatic-speech-recognition","display_name":"Automatic Speech Recognition","score":0.604198},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech Enhancement","score":0.579474},{"id":"https://openalex.org/keywords/statistical-language-modeling","display_name":"Statistical Language Modeling","score":0.569365},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.56112623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.88784426},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7288429},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5722354},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.56112623},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.55463254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5179628},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5009649},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.47995618},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4540336},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3429819},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce53005.2021.9621804","pdf_url":null,"source":{"id":"https://openalex.org/S4363607807","display_name":"2021 IEEE 10th Global Conference on Consumer Electronics (GCCE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality education","score":0.71,"id":"https://metadata.un.org/sdg/4"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":4,"referenced_works":["https://openalex.org/W2019414250","https://openalex.org/W2593730661","https://openalex.org/W2972389417","https://openalex.org/W3133090729"],"related_works":["https://openalex.org/W4245698648","https://openalex.org/W3133710586","https://openalex.org/W2405257913","https://openalex.org/W2401394187","https://openalex.org/W2153098279","https://openalex.org/W2150890698","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2061937230","https://openalex.org/W2026402306"],"abstract_inverted_index":{"Query-by-example":[0],"spoken":[1,174,177],"term":[2],"detection":[3],"(STD)":[4],"systems":[5,63],"can":[6,50,83],"make":[7],"good":[8],"use":[9],"of":[10,44,87],"automatic":[11],"speech":[12,47,117],"recognition":[13],"(ASR),":[14],"especially":[15],"when":[16],"the":[17,26,34,42,85,88,97,122,130,136,142,152,161,170],"error":[18],"rate":[19],"is":[20,159],"low.":[21],"However,":[22],"ASR":[23,35,62,72,81,112,147,165],"suffers":[24],"from":[25],"out-of-vocabulary":[27],"(OOV)":[28],"problem.":[29],"The":[30],"OOV":[31,89,171],"problem":[32,90,172],"in":[33],"stage":[36],"has":[37,75],"a":[38,116],"significant":[39],"impact":[40,86],"on":[41,121],"performance":[43,67,150],"STD":[45,123,143,153],"for":[46,54,173],"retrieval":[48,53,118,149],"and":[49,176],"generate":[51],"false":[52],"query":[55],"words.":[56],"In":[57,102],"recent":[58],"studies,":[59],"End-to-end":[60],"(E2E)":[61],"have":[64],"achieved":[65],"competitive":[66],"compared":[68],"to":[69,115,168],"traditional":[70],"DNN-HMM":[71,156],"systems.":[73],"It":[74],"also":[76],"been":[77],"shown":[78],"that":[79,125,141,163],"E2E":[80,111,146,164],"system":[82],"reduce":[84,169],"by":[91],"using":[92,110,135,145,155],"characters":[93],"or":[94],"sub-words":[95],"as":[96],"output":[98],"unit":[99],"during":[100],"recognition.":[101],"this":[103],"paper,":[104],"we":[105],"propose":[106],"an":[107],"improved":[108],"method":[109,124,144,154],"modeling":[113],"adapted":[114],"task,":[119],"based":[120],"considers":[126],"acoustic":[127],"similarity":[128],"at":[129],"sub-phone":[131],"level.":[132],"Experimental":[133],"results":[134],"NTCIR-12":[137],"SpokenQuery&Doc-2":[138],"task":[139],"show":[140],"improves":[148],"over":[151],"ASR.":[157],"This":[158],"attributed":[160],"fact":[162],"was":[166],"able":[167],"documents":[175],"queries.":[178]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4200203405","counts_by_year":[],"updated_date":"2024-09-14T19:34:35.104191","created_date":"2021-12-31"}
