{"id":"https://openalex.org/W4297841501","doi":"https://doi.org/10.21437/interspeech.2022-10409","title":"Deep LSTM Spoken Term Detection using Wav2Vec 2.0 Recognizer","display_name":"Deep LSTM Spoken Term Detection using Wav2Vec 2.0 Recognizer","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841501","doi":"https://doi.org/10.21437/interspeech.2022-10409"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10409","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10409","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2210.11885","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072542443","display_name":"J\u00e1n \u0160vec","orcid":"https://orcid.org/0000-0001-8362-5927"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan \u0160vec","raw_affiliation_strings":["Department of Cybernetics, University of West Bohemia, Pilsen, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Department of Cybernetics, University of West Bohemia, Pilsen, Czech Republic","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085434299","display_name":"Jan Lehe\u010dka","orcid":"https://orcid.org/0000-0002-3889-8069"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Jan Lehe\u010dka","raw_affiliation_strings":["Department of Cybernetics, University of West Bohemia, Pilsen, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Department of Cybernetics, University of West Bohemia, Pilsen, Czech Republic","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082381758","display_name":"Lubo\u0161 \u0160m\u00eddl","orcid":"https://orcid.org/0000-0002-8169-2410"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lubo\u0161 \u0160m\u00eddl","raw_affiliation_strings":["Department of Cybernetics, University of West Bohemia, Pilsen, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Department of Cybernetics, University of West Bohemia, Pilsen, Czech Republic","institution_ids":["https://openalex.org/I92715842"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5085434299"],"corresponding_institution_ids":["https://openalex.org/I92715842"],"apc_list":null,"apc_paid":null,"fwci":0.5235,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.63921132,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1886","last_page":"1890"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9947999715805054,"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":0.9947999715805054,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9656000137329102,"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":0.8893972635269165},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7255282402038574},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6791539788246155},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5981363654136658},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5832710266113281},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5518362522125244},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.49997854232788086},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48175930976867676},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.4816078841686249},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.4348282814025879},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42854374647140503},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41095179319381714}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8893972635269165},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7255282402038574},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6791539788246155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5981363654136658},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5832710266113281},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5518362522125244},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.49997854232788086},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48175930976867676},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.4816078841686249},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4348282814025879},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42854374647140503},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41095179319381714},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2022-10409","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10409","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2210.11885","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.11885","pdf_url":"https://arxiv.org/pdf/2210.11885","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:dspace5.zcu.cz:11025/51162","is_oa":false,"landing_page_url":"http://hdl.handle.net/11025/51162","pdf_url":null,"source":{"id":"https://openalex.org/S4306400586","display_name":"Digital Library (University of West Bohemia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I92715842","host_organization_name":"University of West Bohemia in Pilsen","host_organization_lineage":["https://openalex.org/I92715842"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"konferen\u010dn\u00ed p\u0159\u00edsp\u011bvek"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2210.11885","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.11885","pdf_url":"https://arxiv.org/pdf/2210.11885","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7200000286102295,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1565198967","https://openalex.org/W1977986156","https://openalex.org/W2000654171","https://openalex.org/W2007261869","https://openalex.org/W2031804986","https://openalex.org/W2111955662","https://openalex.org/W2144588880","https://openalex.org/W2592226044","https://openalex.org/W2689696018","https://openalex.org/W2748394715","https://openalex.org/W2802557066","https://openalex.org/W2970243749","https://openalex.org/W2972613398","https://openalex.org/W2979826702","https://openalex.org/W3015356564","https://openalex.org/W3036601975","https://openalex.org/W3196482042","https://openalex.org/W3197175124"],"related_works":["https://openalex.org/W1534274833","https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2000075989","https://openalex.org/W3117246195","https://openalex.org/W4220683390","https://openalex.org/W156620619"],"abstract_inverted_index":{"In":[0,69],"recent":[1],"years,":[2],"the":[3,12,19,24,31,40,47,53,74,79,101,105,116,120,134,137,149,158,164,167,179],"standard":[4],"hybrid":[5,146,169],"DNN-HMM":[6,145,168],"speech":[7,14,42,76],"recognizers":[8],"are":[9,123],"outperformed":[10],"by":[11,174],"end-to-end":[13],"recognition":[15],"systems.":[16],"One":[17],"of":[18,39,81,89,136,144,151,166],"very":[20],"promising":[21],"approaches":[22],"is":[23,55,63],"grapheme":[25],"Wav2Vec":[26,75],"2.0":[27],"model,":[28,52],"which":[29,99,115],"uses":[30],"self-supervised":[32],"pretraining":[33],"approach":[34,54,131],"combined":[35],"with":[36],"transfer":[37,135],"learning":[38],"fine-tuned":[41],"recognizer.":[43],"Since":[44],"it":[45],"lacks":[46],"pronunciation":[48,111,142],"vocabulary":[49,143],"and":[50,104,119,171,185],"language":[51],"suitable":[56],"for":[57],"tasks":[58],"where":[59],"obtaining":[60],"such":[61],"models":[62],"not":[64],"easy":[65],"or":[66],"almost":[67],"impossible.":[68],"this":[70],"paper,":[71],"we":[72],"use":[73],"recognizer":[77,173],"in":[78,114,140,182],"task":[80],"spoken":[82,90],"term":[83,107,117],"detection":[84],"over":[85],"a":[86,95,109,129,175],"large":[87,176],"set":[88],"documents.":[91],"The":[92,126,154],"method":[93,156],"employs":[94],"deep":[96],"LSTM":[97],"network":[98],"maps":[100],"recognized":[102],"hypothesis":[103],"searched":[106],"into":[108,148],"shared":[110],"embedding":[112],"space":[113],"occurrences":[118],"assigned":[121],"scores":[122],"easily":[124],"computed.":[125],"paper":[127],"describes":[128],"bootstrapping":[130],"that":[132],"allows":[133],"knowledge":[138],"contained":[139],"traditional":[141],"ASR":[147,170],"context":[150],"grapheme-based":[152],"Wav2Vec.":[153],"proposed":[155],"outperforms":[157],"previously":[159],"published":[160],"system":[161],"based":[162],"on":[163,178],"combination":[165],"phoneme":[172],"margin":[177],"MALACH":[180],"data":[181],"both":[183],"English":[184],"Czech":[186],"languages.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
