{"id":"https://openalex.org/W7107878390","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249276","title":"Language Adaptation Wake Word Spotting via Latent Space from Pre-Trained Speech Models","display_name":"Language Adaptation Wake Word Spotting via Latent Space from Pre-Trained Speech Models","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W7107878390","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249276"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249276","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":null,"display_name":"Shifu Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shifu Xiong","raw_affiliation_strings":["University of Science and Technology of China,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hengshun Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110780","display_name":"HUI Research (Sweden)","ror":"https://ror.org/021t57y21","country_code":"SE","type":"company","lineage":["https://openalex.org/I4210110780"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Hengshun Zhou","raw_affiliation_strings":["iFlytek Research,Hefei,Anhui,P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFlytek Research,Hefei,Anhui,P. R. China","institution_ids":["https://openalex.org/I4210110780"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kai Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110780","display_name":"HUI Research (Sweden)","ror":"https://ror.org/021t57y21","country_code":"SE","type":"company","lineage":["https://openalex.org/I4210110780"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Kai Shen","raw_affiliation_strings":["iFlytek Research,Hefei,Anhui,P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFlytek Research,Hefei,Anhui,P. R. China","institution_ids":["https://openalex.org/I4210110780"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shi Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110780","display_name":"HUI Research (Sweden)","ror":"https://ror.org/021t57y21","country_code":"SE","type":"company","lineage":["https://openalex.org/I4210110780"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Shi Cheng","raw_affiliation_strings":["iFlytek Research,Hefei,Anhui,P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFlytek Research,Hefei,Anhui,P. R. China","institution_ids":["https://openalex.org/I4210110780"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hang Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Chen","raw_affiliation_strings":["University of Science and Technology of China,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Genshun Wan","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Genshun Wan","raw_affiliation_strings":["University of Science and Technology of China,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kewei Li","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kewei Li","raw_affiliation_strings":["University of Science and Technology of China,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jun Du","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":null,"display_name":"Lirong Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lirong Dai","raw_affiliation_strings":["University of Science and Technology of China,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"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":0.7456901,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"519","last_page":"524"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8844000101089478,"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":0.8844000101089478,"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 and Audio Processing","score":0.040699999779462814,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.012299999594688416,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.6722999811172485},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.538100004196167},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4936000108718872},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4693000018596649},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.45829999446868896},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4510999917984009},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.400299996137619},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.38359999656677246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7577999830245972},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.6722999811172485},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6420000195503235},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5501000285148621},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.538100004196167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5370000004768372},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4936000108718872},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4693000018596649},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.45829999446868896},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4510999917984009},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.400299996137619},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.38359999656677246},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3531999886035919},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C21036866","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2957000136375427},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.28540000319480896},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.2793000042438507}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249276","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.723456621170044}],"awards":[{"id":"https://openalex.org/G5422811002","display_name":null,"funder_award_id":"U23A20315","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5586136776","display_name":null,"funder_award_id":"2022YFB4500600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program 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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2034940213","https://openalex.org/W2587529061","https://openalex.org/W2939412000","https://openalex.org/W2963125010","https://openalex.org/W2963977978","https://openalex.org/W3015273269","https://openalex.org/W3203140070","https://openalex.org/W3204696009","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221141391","https://openalex.org/W4224821750","https://openalex.org/W4224916413","https://openalex.org/W4296068585","https://openalex.org/W4296069135","https://openalex.org/W4297841921","https://openalex.org/W4372260355","https://openalex.org/W4372267500","https://openalex.org/W4372268294","https://openalex.org/W4372270236","https://openalex.org/W4372339449","https://openalex.org/W4372346399","https://openalex.org/W4375868863","https://openalex.org/W4375868905","https://openalex.org/W4375869070","https://openalex.org/W4385485026","https://openalex.org/W4385822254","https://openalex.org/W4385822411","https://openalex.org/W4385823066","https://openalex.org/W4391021675","https://openalex.org/W4392909943"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"approach":[4,102],"for":[5,46],"multilingual":[6,88],"Wake":[7],"Word":[8],"Spotting":[9],"(WWS),":[10],"ingeniously":[11],"fusing":[12],"pre-trained":[13,69],"extensive":[14],"speech":[15,70],"models":[16],"with":[17,35],"tailored":[18,45],"hidden":[19],"units":[20],"dedicated":[21],"to":[22,50,59],"WWS.":[23,48,89,108],"Initially,":[24],"the":[25,52,64,68,83,97,100,105],"Whisper":[26],"encoder":[27],"functions":[28],"as":[29],"a":[30,36,42],"spatial":[31],"cornerstone,":[32],"seamlessly":[33],"integrating":[34],"lightweight":[37],"ShuffleNet-based":[38],"encoder,":[39],"followed":[40],"by":[41],"shared":[43],"decoder":[44],"mono-lingual":[47],"Then,":[49],"refine":[51],"encoder's":[53],"capability,":[54],"k-means":[55],"clustering":[56],"is":[57],"leveraged":[58],"extract":[60],"aligned":[61],"targets":[62],"from":[63],"latent":[65],"space":[66],"of":[67,99,107],"model,":[71],"thereby":[72],"bolstering":[73],"monolingual":[74],"performance.":[75],"Finally,":[76],"linguistic":[77],"priors":[78],"are":[79],"adaptively":[80],"incorporated":[81],"into":[82],"proposed":[84,101],"framework,":[85],"facilitating":[86],"effective":[87],"Experimental":[90],"evaluations":[91],"in":[92,103],"Spanish":[93],"and":[94],"Arabic":[95],"demonstrate":[96],"proficiency":[98],"enhancing":[104],"performance":[106]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}