{"id":"https://openalex.org/W4224932156","doi":"https://doi.org/10.1109/icassp43922.2022.9746647","title":"Text Adaptive Detection for Customizable Keyword Spotting","display_name":"Text Adaptive Detection for Customizable Keyword Spotting","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224932156","doi":"https://doi.org/10.1109/icassp43922.2022.9746647"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746647","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746647","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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/A5103250176","display_name":"Yu Xi","orcid":"https://orcid.org/0000-0003-0498-0328"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yu Xi","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab","MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101667381","display_name":"Tian Tan","orcid":"https://orcid.org/0000-0002-4723-0044"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian Tan","raw_affiliation_strings":["AISpeech Ltd,Suzhou,China","AISpeech Ltd, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"AISpeech Ltd,Suzhou,China","institution_ids":[]},{"raw_affiliation_string":"AISpeech Ltd, Suzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071937621","display_name":"Wangyou Zhang","orcid":"https://orcid.org/0000-0003-4500-3515"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangyou Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab","MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086417695","display_name":"Baochen Yang","orcid":"https://orcid.org/0000-0002-0494-0361"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baochen Yang","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab","MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab","MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103250176"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":1.2525,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.81162877,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6652","last_page":"6656"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9986000061035156,"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":0.9983999729156494,"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/keyword-spotting","display_name":"Keyword spotting","score":0.941630482673645},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8009078502655029},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.7305242419242859},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5879553556442261},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5480844378471375},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5368607044219971},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5329903960227966},{"id":"https://openalex.org/keywords/f1-score","display_name":"F1 score","score":0.45046988129615784},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4412824213504791},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3379098176956177}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.941630482673645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8009078502655029},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.7305242419242859},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5879553556442261},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5480844378471375},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5368607044219971},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5329903960227966},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.45046988129615784},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4412824213504791},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3379098176956177},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746647","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746647","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1983205135","https://openalex.org/W2000654171","https://openalex.org/W2034940213","https://openalex.org/W2145215282","https://openalex.org/W2155027007","https://openalex.org/W2156431836","https://openalex.org/W2167338739","https://openalex.org/W2208299922","https://openalex.org/W2407023693","https://openalex.org/W2507580616","https://openalex.org/W2510945575","https://openalex.org/W2517251061","https://openalex.org/W2578392894","https://openalex.org/W2587529061","https://openalex.org/W2652238127","https://openalex.org/W2797759721","https://openalex.org/W2888951652","https://openalex.org/W2938873567","https://openalex.org/W2962707338","https://openalex.org/W2963308316","https://openalex.org/W2963414149","https://openalex.org/W2972613398","https://openalex.org/W3095694146","https://openalex.org/W3098773154","https://openalex.org/W3155772857","https://openalex.org/W3163074978","https://openalex.org/W3163582231","https://openalex.org/W3196509839","https://openalex.org/W6631362777","https://openalex.org/W6659477065","https://openalex.org/W6683204974","https://openalex.org/W6688039610","https://openalex.org/W6795661435"],"related_works":["https://openalex.org/W1208717","https://openalex.org/W10064791","https://openalex.org/W8315361","https://openalex.org/W7655147","https://openalex.org/W4781179","https://openalex.org/W7120470","https://openalex.org/W10412386","https://openalex.org/W2433769","https://openalex.org/W5192282","https://openalex.org/W2131697"],"abstract_inverted_index":{"Always-on":[0],"keyword":[1,132],"spotting":[2,133],"(KWS),":[3],"i.e.,":[4],"wake":[5],"word":[6,24],"detection,":[7],"has":[8,31],"been":[9],"widely":[10],"used":[11,100],"in":[12,58,156],"many":[13],"voice":[14],"assistant":[15],"applications":[16],"running":[17],"on":[18,27,46,130],"smart":[19],"devices.":[20],"Although":[21],"fixed":[22],"wakeup":[23],"detection":[25,44,66,81,89,115,127,146,158],"trained":[26],"specifically":[28],"collected":[29],"data":[30],"reached":[32],"high":[33],"performance,":[34],"it":[35],"is":[36,68,99],"still":[37],"challenging":[38],"to":[39,55,83,103,119,162],"build":[40],"an":[41,150],"arbitrarily":[42],"customizable":[43],"system":[45],"general":[47],"found":[48],"data.":[49],"A":[50],"deep":[51],"learning":[52],"classifier,":[53],"similar":[54],"the":[56,65,96,121,143,157,163],"one":[57],"speech":[59],"recognition,":[60],"can":[61,148],"be":[62],"used,":[63],"but":[64],"performance":[67],"usually":[69],"significantly":[70],"degraded.":[71],"In":[72],"this":[73],"work,":[74],"we":[75],"propose":[76],"a":[77,88,92,108,131],"novel":[78],"text":[79,97,144],"adaptive":[80,145],"framework":[82,147],"directly":[84,125],"formulate":[85],"KWS":[86],"as":[87,101],"rather":[90],"than":[91],"classification":[93],"problem.":[94],"Here,":[95],"prompt":[98],"input":[102],"promote":[104],"biased":[105],"classification,":[106],"and":[107,112,124],"series":[109],"of":[110,135,154],"frame":[111],"sequence":[113],"level":[114],"criteria":[116],"are":[117],"employed":[118],"replace":[120],"cross-entropy":[122],"criterion":[123],"optimize":[126],"performance.":[128],"Experiments":[129],"version":[134],"Wall":[136],"Street":[137],"Journal":[138],"(WSJ)":[139],"dataset":[140],"show":[141],"that":[142],"achieve":[149],"average":[151],"relative":[152],"improvement":[153],"16.88%":[155],"metric":[159],"F1-score":[160],"compared":[161],"baseline":[164],"model.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}