{"id":"https://openalex.org/W4416799457","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249196","title":"Introducing Self-Supervised Learning Models for Spoken Query-Spoken Term Detection","display_name":"Introducing Self-Supervised Learning Models for Spoken Query-Spoken Term Detection","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799457","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249196"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249196","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249196","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":"Masato Nagase","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113300","display_name":"Research Institute for Environmental Sciences and Public Health of Iwate Prefecture","ror":"https://ror.org/01y16qn61","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210113300"]},{"id":"https://openalex.org/I6090238","display_name":"Iwate Prefectural University","ror":"https://ror.org/054dx8336","country_code":"JP","type":"education","lineage":["https://openalex.org/I6090238"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Nagase","raw_affiliation_strings":["Iwate Prefecture University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Iwate Prefecture University,Japan","institution_ids":["https://openalex.org/I6090238","https://openalex.org/I4210113300"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110949984","display_name":"Kazunori Kojima","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113300","display_name":"Research Institute for Environmental Sciences and Public Health of Iwate Prefecture","ror":"https://ror.org/01y16qn61","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210113300"]},{"id":"https://openalex.org/I6090238","display_name":"Iwate Prefectural University","ror":"https://ror.org/054dx8336","country_code":"JP","type":"education","lineage":["https://openalex.org/I6090238"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazunori Kojima","raw_affiliation_strings":["Iwate Prefecture University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Iwate Prefecture University,Japan","institution_ids":["https://openalex.org/I6090238","https://openalex.org/I4210113300"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071262282","display_name":"Shi-wook Lee","orcid":"https://orcid.org/0000-0002-2377-6376"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shi-wook Lee","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology,Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yosiaki Itoh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113300","display_name":"Research Institute for Environmental Sciences and Public Health of Iwate Prefecture","ror":"https://ror.org/01y16qn61","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210113300"]},{"id":"https://openalex.org/I6090238","display_name":"Iwate Prefectural University","ror":"https://ror.org/054dx8336","country_code":"JP","type":"education","lineage":["https://openalex.org/I6090238"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yosiaki Itoh","raw_affiliation_strings":["Iwate Prefecture University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Iwate Prefecture University,Japan","institution_ids":["https://openalex.org/I6090238","https://openalex.org/I4210113300"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.17652462,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"653","last_page":"657"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8490999937057495,"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":0.8490999937057495,"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/T12031","display_name":"Speech and dialogue systems","score":0.049400001764297485,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.024900000542402267,"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/term","display_name":"Term (time)","score":0.583299994468689},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5537999868392944},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5473999977111816},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5329999923706055},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4894999861717224},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.365200012922287},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3522999882698059},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.33169999718666077}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7858999967575073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6061999797821045},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.583299994468689},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5537999868392944},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5473999977111816},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5329999923706055},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5245000123977661},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5188000202178955},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4894999861717224},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.365200012922287},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3199000060558319},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.29280000925064087},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249196","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249196","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2766219058","https://openalex.org/W2963194026","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4372346399"],"related_works":[],"abstract_inverted_index":{"This":[0],"study":[1],"was":[2],"undertaken":[3],"to":[4],"improve":[5],"the":[6,24,47,51,84,100,103,106],"performance":[7],"of":[8,65,102],"Spoken":[9,11],"Query":[10],"Term":[12],"Detection":[13],"(SQ-STD)":[14],"by":[15],"introducing":[16],"Self-Supervised":[17],"Learning":[18],"(SSL)":[19],"models.":[20],"To":[21],"construct":[22],"posteriorgrams,":[23],"SSL":[25,63],"models":[26,64],"are":[27],"augmented":[28],"with":[29],"a":[30],"Connectionist":[31],"Temporal":[32],"Classification":[33],"(CTC)":[34],"layer":[35,48],"and":[36,78],"extracted":[37],"posterior":[38],"probability":[39],"vectors,":[40],"which":[41,98],"represent":[42],"phonemes":[43],"or":[44],"syllables":[45],"from":[46,62],"immediately":[49],"preceding":[50],"CTC":[52],"output":[53],"layer.":[54],"Posteriorgram":[55],"matching":[56],"is":[57,99],"performed":[58],"using":[59],"posteriorgrams":[60],"generated":[61],"three":[66],"types":[67],"known":[68],"for":[69,105],"their":[70],"high":[71],"speech":[72],"recognition":[73],"accuracy:":[74],"wav2vec":[75],"2.0,":[76],"HuBERT,":[77],"WavLM.":[79],"Experiment":[80],"results":[81],"obtained":[82],"on":[83],"NTCIR":[85],"evaluation":[86],"sets":[87],"demonstrate":[88],"that":[89],"our":[90],"approach":[91],"achieves":[92],"retrieval":[93],"accuracy":[94],"exceeding":[95],"92":[96],"%,":[97],"state":[101],"art":[104],"evolution":[107],"sets.":[108]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}