{"id":"https://openalex.org/W7213601735","doi":"https://doi.org/10.48550/arxiv.2609.20070","title":"CircleMatch: Prototype Matching with Circular Temporal Statistics for Tiny Keyword Spotting","display_name":"CircleMatch: Prototype Matching with Circular Temporal Statistics for Tiny Keyword Spotting","publication_year":2026,"publication_date":"2026-09-17","ids":{"openalex":"https://openalex.org/W7213601735","doi":"https://doi.org/10.48550/arxiv.2609.20070"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2609.20070","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.20070","pdf_url":"https://arxiv.org/pdf/2609.20070","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.20070","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148083286","display_name":"Jiajun Sun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sun, Jiajun","raw_affiliation_strings":["Shanghai Normal University , Shanghai , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Normal University , Shanghai , China","institution_ids":["https://openalex.org/I21945476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5152114767","display_name":"Zhe Gao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gao, Zhe","raw_affiliation_strings":["Shanghai Normal University , Shanghai , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Normal University , Shanghai , China","institution_ids":["https://openalex.org/I21945476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I21945476"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.9940999746322632,"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":0.9940999746322632,"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":0.0034000000450760126,"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/T11309","display_name":"Music and Audio Processing","score":0.0010000000474974513,"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":0.9340000152587891},{"id":"https://openalex.org/keywords/prototype-matching","display_name":"prototype matching","score":0.7839999794960022},{"id":"https://openalex.org/keywords/time-compression","display_name":"time compression","score":0.4390000104904175},{"id":"https://openalex.org/keywords/voice-commands","display_name":"voice commands","score":0.44200000166893005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.727400004863739},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6784999966621399},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.6531999707221985},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.5776000022888184},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5733000040054321},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.567300021648407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5436999797821045},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.504800021648407},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4803999960422516},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.47609999775886536},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46399998664855957},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.426800012588501},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41850000619888306},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3806999921798706},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.3596000075340271},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C158096908","wikidata":"https://www.wikidata.org/wiki/Q3983303","display_name":"Template matching","level":3,"score":0.2567000091075897}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.20070","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.20070","pdf_url":"https://arxiv.org/pdf/2609.20070","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.20070","doi":"https://doi.org/10.48550/arxiv.2609.20070","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.20070","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.20070","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.20070","pdf_url":"https://arxiv.org/pdf/2609.20070","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","score":0.7098514437675476,"display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213601735.pdf","grobid_xml":"https://content.openalex.org/works/W7213601735.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Keyword":[0],"spotting":[1],"(KWS),":[2],"the":[3,104,117,124],"task":[4],"of":[5,15,123,143],"identifying":[6],"predefined":[7],"words":[8],"in":[9,103],"speech,":[10],"is":[11],"a":[12,35],"core":[13],"capability":[14],"voice-enabled":[16],"devices.":[17],"Achieving":[18],"high":[19],"KWS":[20,39],"accuracy":[21,131],"under":[22],"tight":[23],"parameter":[24],"budgets":[25],"across":[26],"different":[27],"vocabulary":[28],"sizes":[29],"remains":[30],"challenging.":[31],"We":[32,86],"present":[33],"CircleMatch,":[34],"matching":[36],"framework":[37],"enabling":[38],"with":[40,108,132],"very":[41],"few":[42],"parameters.":[43],"Its":[44],"encoder":[45],"independently":[46],"compresses":[47],"frequency":[48],"bands":[49],"and":[50,77,81,94,116,119,146,152],"fuses":[51],"them":[52],"into":[53],"frame":[54],"features.":[55],"These":[56],"features":[57],"are":[58,155],"then":[59],"matched":[60],"against":[61],"learned":[62],"class-specific":[63],"prototypes":[64],"to":[65,100,148],"produce":[66],"temporal":[67,149],"response":[68,79],"curves.":[69],"Parameter-free":[70],"circular":[71],"aggregation":[72],"encodes":[73],"time":[74],"as":[75],"angles":[76],"summarizes":[78],"distributions":[80],"relative":[82],"timing":[83],"for":[84],"classification.":[85],"develop":[87],"four":[88],"tiny":[89,133],"variants,":[90],"Circle-D4,":[91],"Circle-D8,":[92],"Circle-D16,":[93],"Circle-D32,":[95],"ranging":[96],"from":[97],"approximately":[98],"1k":[99],"7k":[101],"parameters":[102],"12-class":[105],"setting.":[106],"Experiments":[107],"multiple":[109],"random":[110],"seeds":[111],"on":[112],"Speech":[113],"Commands":[114],"v1/v2":[115],"English":[118],"Spanish":[120],"Micro":[121],"subsets":[122],"Multilingual":[125],"Spoken":[126],"Words":[127],"Corpus":[128],"demonstrate":[129],"competitive":[130],"models.":[134],"Our":[135],"qualitative":[136],"analysis":[137],"further":[138],"suggests":[139],"approximate":[140],"shift":[141],"equivariance":[142],"prototype":[144],"responses":[145],"adaptation":[147],"compression.":[150],"Code":[151],"model":[153],"weights":[154],"available":[156],"at":[157],"https://github.com/ora942878/CircleMatch.":[158]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2026-09-19T00:00:00"}