{"id":"https://openalex.org/W4221000292","doi":"https://doi.org/10.1142/s2717554522500059","title":"Keyword Search Based on Unsupervised Pre-Trained Acoustic Models","display_name":"Keyword Search Based on Unsupervised Pre-Trained Acoustic Models","publication_year":2021,"publication_date":"2021-09-01","ids":{"openalex":"https://openalex.org/W4221000292","doi":"https://doi.org/10.1142/s2717554522500059"},"language":"en","primary_location":{"id":"doi:10.1142/s2717554522500059","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s2717554522500059","pdf_url":null,"source":{"id":"https://openalex.org/S4210231678","display_name":"International Journal of Asian Language Processing","issn_l":"2424-791X","issn":["2424-791X","2717-5545"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Asian 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/A5086921718","display_name":"Xiner Li","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiner Li","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing 100084, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing 100084, P. R. China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065846668","display_name":"Jing Zhao","orcid":"https://orcid.org/0000-0003-0158-5330"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhao","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing 100084, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing 100084, P. R. China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100692904","display_name":"Wei-Qiang Zhang","orcid":"https://orcid.org/0000-0003-3841-1959"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei-Qiang Zhang","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing 100084, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing 100084, P. R. China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033243530","display_name":"Zhiqiang Lv","orcid":"https://orcid.org/0000-0002-3071-160X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Lv","raw_affiliation_strings":["TEG AI, Tencent Inc, Beijing 100193, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TEG AI, Tencent Inc, Beijing 100193, P. R. China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108615106","display_name":"Shen Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shen Huang","raw_affiliation_strings":["TEG AI, Tencent Inc, Beijing 100193, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TEG AI, Tencent Inc, Beijing 100193, P. R. China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100692904"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.1365,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57932476,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"31","issue":"03n04","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9977999925613403,"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":0.9909999966621399,"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":0.8122860193252563},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6492081880569458},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6357452869415283},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5651461482048035},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5330191254615784},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4686279594898224},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4542071223258972},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4487888514995575},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.44499528408050537},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4264650344848633},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34233617782592773},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3218722343444824}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8122860193252563},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6492081880569458},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6357452869415283},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5651461482048035},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5330191254615784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4686279594898224},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4542071223258972},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4487888514995575},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.44499528408050537},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4264650344848633},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34233617782592773},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3218722343444824},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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},{"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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s2717554522500059","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s2717554522500059","pdf_url":null,"source":{"id":"https://openalex.org/S4210231678","display_name":"International Journal of Asian Language Processing","issn_l":"2424-791X","issn":["2424-791X","2717-5545"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Asian Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4401023024","display_name":null,"funder_award_id":"BNR2019TD01022","funder_id":"https://openalex.org/F4320329777","funder_display_name":"Beijing National Research Center For Information Science And Technology"},{"id":"https://openalex.org/G6450856609","display_name":null,"funder_award_id":"U1836219","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329777","display_name":"Beijing National Research Center For Information Science And Technology","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1488355515","https://openalex.org/W1494198834","https://openalex.org/W2034940213","https://openalex.org/W2101346879","https://openalex.org/W2127141656","https://openalex.org/W2133290121","https://openalex.org/W2159436188","https://openalex.org/W2963242190","https://openalex.org/W2963292011","https://openalex.org/W3015503328","https://openalex.org/W3108655343","https://openalex.org/W3155772857"],"related_works":["https://openalex.org/W1963734729","https://openalex.org/W1539050421","https://openalex.org/W2126560900","https://openalex.org/W2101346879","https://openalex.org/W2117523216","https://openalex.org/W3119155061","https://openalex.org/W4287548803","https://openalex.org/W3037322406","https://openalex.org/W1563147278","https://openalex.org/W2395078704"],"abstract_inverted_index":{"Speech":[0,70],"keyword":[1,26,58,126,139,223],"search":[2,127,224],"(KWS)":[3],"is":[4,40,88,102],"the":[5,10,22,65,106,120,130,165,168,173,179,182,201,217],"task":[6,23],"of":[7,24,32,83,99,111,122,170,181,222],"automatically":[8],"detecting":[9],"required":[11],"keywords":[12],"in":[13,61,80,93,193],"continuous":[14],"speech.":[15],"Single-keyword":[16],"detection":[17],"can":[18,197,204],"be":[19,198,205],"regarded":[20],"as":[21],"speech":[25,36,50,57,138],"wake-up.":[27],"For":[28,53],"many":[29],"practical":[30],"applications":[31],"these":[33],"small":[34],"vocabulary":[35,49],"recognition":[37,51],"tasks,":[38],"it":[39],"costly":[41],"and":[42,125,133,219],"unnecessary":[43],"to":[44,56,89,104,207],"build":[45],"a":[46,81,96],"full":[47],"large":[48,97],"system.":[52],"tasks":[54,113],"related":[55],"search,":[59],"insufficiency":[60],"data":[62,101,110],"resources":[63],"remains":[64],"main":[66],"challenge":[67],"so":[68],"far.":[69],"pre-training":[71,124,136],"has":[72],"become":[73],"an":[74],"effective":[75,91],"technique,":[76],"showing":[77],"its":[78],"superiority":[79],"variety":[82],"tasks.":[84],"The":[85,141,150],"key":[86],"idea":[87],"learn":[90],"representations":[92],"settings":[94],"where":[95],"amount":[98],"unlabeled":[100],"available":[103],"improve":[105],"performance":[107,175,180,210],"while":[108,178],"labeled":[109],"downstream":[112],"are":[114],"limited.":[115],"This":[116,215],"research":[117,142,151],"focuses":[118],"on":[119,129,211,226],"combination":[121],"unsupervised":[123,135,227],"based":[128,225],"Keyword-Filler":[131],"model":[132,145,161,185,203],"introduces":[134],"into":[137],"search.":[140],"selects":[143],"pre-trained":[144,160,183,202],"architecture":[146],"Wav2vec2.0":[147],"including":[148],"XLSR.":[149],"results":[152],"show":[153],"that":[154,200],"training":[155],"with":[156],"feature":[157],"extracted":[158],"by":[159],"performs":[162],"better":[163,209],"than":[164],"baseline.":[166],"In":[167],"case":[169],"low-resource":[171],"condition,":[172],"baseline":[174],"drops":[176],"significantly,":[177],"tuned":[184,206],"does":[186],"not":[187],"decrease":[188],"but":[189],"even":[190],"increases":[191],"slightly":[192],"some":[194],"intervals.":[195],"It":[196],"seen":[199],"achieve":[208],"very":[212],"little":[213],"data.":[214],"shows":[216],"advantage":[218],"application":[220],"value":[221],"pre-training.":[228]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}