{"id":"https://openalex.org/W4416798476","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249226","title":"Lightweight Zero-Shot Keyword Spotting via Multi-Granular Knowledge Distillation","display_name":"Lightweight Zero-Shot Keyword Spotting via Multi-Granular Knowledge Distillation","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798476","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249226"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249226","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249226","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":"Yun-Ting Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yun-Ting Sun","raw_affiliation_strings":["National Taiwan Normal University,Department of Computer Science and Information Engineering,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Department of Computer Science and Information Engineering,Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084004535","display_name":"Lo-Ya Li","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Lo-Ya Li","raw_affiliation_strings":["Institute of AI Interdisciplinary Applied Technology, National Taiwan Normal University,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of AI Interdisciplinary Applied Technology, National Taiwan Normal University,Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110596981","display_name":"Tien-Hong Lo","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tien-Hong Lo","raw_affiliation_strings":["National Taiwan Normal University,Department of Computer Science and Information Engineering,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Department of Computer Science and Information Engineering,Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019048236","display_name":"Jeih-weih Hung","orcid":"https://orcid.org/0000-0001-9366-3070"},"institutions":[{"id":"https://openalex.org/I193365169","display_name":"National Chi Nan University","ror":"https://ror.org/03ha6v181","country_code":"TW","type":"education","lineage":["https://openalex.org/I193365169"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jeih-Weih Hung","raw_affiliation_strings":["National Chi Nan University,Department of Electrical Engineering,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Chi Nan University,Department of Electrical Engineering,Taiwan","institution_ids":["https://openalex.org/I193365169"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104352144","display_name":"Shih-Chieh Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I901624438","display_name":"Realtek (Taiwan)","ror":"https://ror.org/05x1ffr83","country_code":"TW","type":"company","lineage":["https://openalex.org/I901624438"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shih-Chieh Huang","raw_affiliation_strings":["Realtek Semiconductor Corp.,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Realtek Semiconductor Corp.,Taiwan","institution_ids":["https://openalex.org/I901624438"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115595070","display_name":"Berlin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Berlin Chen","raw_affiliation_strings":["National Taiwan Normal University,Department of Computer Science and Information Engineering,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Department of Computer Science and Information Engineering,Taiwan","institution_ids":["https://openalex.org/I134161618"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"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":0.17626798,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1182","last_page":"1187"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9575999975204468,"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":0.9575999975204468,"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":0.01489999983459711,"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/T10863","display_name":"Voice and Speech Disorders","score":0.006200000178068876,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5674999952316284},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4997999966144562},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.49000000953674316},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.4528000056743622},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.44449999928474426},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.4302000105381012},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.4131999909877777},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.37439998984336853},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.3711000084877014}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8184000253677368},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5674999952316284},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4997999966144562},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.49000000953674316},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.4528000056743622},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.44449999928474426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44290000200271606},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.4302000105381012},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.4131999909877777},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.37439998984336853},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.3711000084877014},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3698999881744385},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3684999942779541},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.3433000147342682},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33489999175071716},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.30720001459121704},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2973000109195709},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27720001339912415},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2596000134944916},{"id":"https://openalex.org/C2781390188","wikidata":"https://www.wikidata.org/wiki/Q25203449","display_name":"Spike (software development)","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249226","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249226","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":18,"referenced_works":["https://openalex.org/W2407386500","https://openalex.org/W2963736842","https://openalex.org/W2973133192","https://openalex.org/W3008790380","https://openalex.org/W3015399080","https://openalex.org/W3046052470","https://openalex.org/W3096235116","https://openalex.org/W4372346399","https://openalex.org/W4385822415","https://openalex.org/W4385822437","https://openalex.org/W4385823483","https://openalex.org/W4390873312","https://openalex.org/W4391021514","https://openalex.org/W4392902956","https://openalex.org/W4392904395","https://openalex.org/W4402112589","https://openalex.org/W4406859109","https://openalex.org/W4408353194"],"related_works":[],"abstract_inverted_index":{"Zero-shot":[0],"keyword":[1],"spotting":[2],"(ZSKWS)":[3],"allows":[4],"voice":[5],"interfaces":[6],"to":[7,65,82,117,142],"recognize":[8],"user-defined":[9],"keywords":[10],"without":[11],"enrollment":[12],"audio;":[13],"however,":[14],"deploying":[15],"such":[16],"models":[17],"on":[18,54],"embedded":[19],"hardware":[20],"is":[21],"challenging":[22],"because":[23],"memory":[24],"and":[25,57,109],"compute":[26],"budgets":[27],"are":[28],"severely":[29],"limited.":[30],"In":[31],"this":[32,36],"paper,":[33],"we":[34,43,74],"address":[35],"constraint":[37],"through":[38,87],"two":[39],"complementary":[40],"countermeasures.":[41],"First,":[42],"compress":[44],"the":[45,62,83,88,122,125,131,137,149,152],"acoustic":[46],"front":[47],"end":[48],"with":[49,121],"LiCo-Net-a":[50],"compact":[51],"encoder":[52],"built":[53],"depthwiseseparable":[55],"convolutions":[56],"linear":[58],"activations":[59],"that":[60],"reduces":[61,130],"model":[63,81,129,156],"footprint":[64],"under":[66,158],"0.5":[67],"MB":[68],"while":[69],"delivering":[70],"efficient":[71],"performance.":[72],"Second,":[73],"transfer":[75],"knowledge":[76,153],"from":[77,140],"a":[78],"high-capacity":[79],"teacher":[80],"lightweight":[84,127],"student":[85],"one":[86],"synergy":[89],"of":[90,136,151],"multi-level":[91],"distillation":[92],"losses:":[93],"(i)":[94],"mean":[95],"squared":[96],"error":[97,133],"(MSE)":[98],"in":[99,106],"utterance-level":[100],"logits,":[101],"(ii)":[102],"Kullback-Leibler":[103],"(KL)":[104],"divergence":[105],"phoneme-level":[107],"probabilities,":[108],"(iii)":[110],"Noise":[111],"Contrastive":[112],"Estimation":[113],"(InfoNCE)":[114],"loss":[115],"applied":[116],"intermediate":[118],"features.":[119],"Notably,":[120],"MSE+KL":[123],"combination,":[124],"resulting":[126],"ZSKWS":[128,155],"equal":[132],"rate":[134],"(EER)":[135],"Qualcomm":[138],"dataset":[139],"16.8%":[141],"10.7%":[143],"(a":[144],"36%":[145],"relative":[146],"reduction),":[147],"demonstrating":[148],"practicality":[150],"distillation-empowered":[154],"even":[157],"stringent":[159],"resource":[160],"constraints.":[161]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}