{"id":"https://openalex.org/W4408354367","doi":"https://doi.org/10.1109/icassp49660.2025.10890010","title":"Streaming Keyword Spotting Boosted by Cross-layer Discrimination Consistency","display_name":"Streaming Keyword Spotting Boosted by Cross-layer Discrimination Consistency","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354367","doi":"https://doi.org/10.1109/icassp49660.2025.10890010"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890010","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101329732","display_name":"Yu Xi","orcid":"https://orcid.org/0000-0002-9725-5063"},"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":"Yu Xi","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078072988","display_name":"Haoyu Li","orcid":"https://orcid.org/0009-0001-8096-4664"},"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":"Haoyu Li","raw_affiliation_strings":["AISpeech Ltd,Suzhou,China","Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AISpeech Ltd,Suzhou,China","institution_ids":[]},{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015718206","display_name":"Xiaoyu Gu","orcid":"https://orcid.org/0000-0003-2929-2441"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoyu Gu","raw_affiliation_strings":["AISpeech Ltd,Suzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AISpeech Ltd,Suzhou,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348486","display_name":"Hao Li","orcid":"https://orcid.org/0000-0003-4468-5972"},"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":"Hao Li","raw_affiliation_strings":["AISpeech Ltd,Suzhou,China","Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AISpeech Ltd,Suzhou,China","institution_ids":[]},{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111432082","display_name":"Yidi Jiang","orcid":"https://orcid.org/0000-0002-2317-9571"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yidi Jiang","raw_affiliation_strings":["National University of Singapore,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"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,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9871000051498413,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9871000051498413,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.8028004169464111},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.7021416425704956},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6584985256195068},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6280492544174194},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5016860961914062},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34986478090286255},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.0782354474067688},{"id":"https://openalex.org/keywords/composite-material","display_name":"Composite material","score":0.05072340369224548}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8028004169464111},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.7021416425704956},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6584985256195068},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6280492544174194},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5016860961914062},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34986478090286255},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0782354474067688},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.05072340369224548}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890010","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5899999737739563,"display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2034940213","https://openalex.org/W2127141656","https://openalex.org/W2407080277","https://openalex.org/W2510945575","https://openalex.org/W2748659049","https://openalex.org/W2797759721","https://openalex.org/W2936774411","https://openalex.org/W2963308316","https://openalex.org/W2963628261","https://openalex.org/W2963977978","https://openalex.org/W2972541922","https://openalex.org/W3015210390","https://openalex.org/W3096976027","https://openalex.org/W3161425572","https://openalex.org/W3162249256","https://openalex.org/W3163237592","https://openalex.org/W3197140813","https://openalex.org/W3205920203","https://openalex.org/W3207815550","https://openalex.org/W4206567542","https://openalex.org/W4224932156","https://openalex.org/W4372259817","https://openalex.org/W4372267500","https://openalex.org/W4391021514","https://openalex.org/W4392904393","https://openalex.org/W4392904484","https://openalex.org/W4392932011","https://openalex.org/W4402111963","https://openalex.org/W4402112042","https://openalex.org/W4408352627","https://openalex.org/W6637516147","https://openalex.org/W6638749077","https://openalex.org/W6774097463"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W4286904253","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W3206647229","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2545741539","https://openalex.org/W1989658893"],"abstract_inverted_index":{"Connectionist":[0],"Temporal":[1],"Classification":[2],"(CTC),":[3],"a":[4,61,78,151,166],"non-autoregressive":[5],"training":[6],"criterion,":[7],"is":[8],"widely":[9],"used":[10],"in":[11,155],"online":[12],"keyword":[13,91],"spotting":[14],"(KWS).":[15],"However,":[16],"existing":[17],"CTC-based":[18,73],"KWS":[19,134,163],"decoding":[20,47,63,82,128,138],"strategies":[21],"either":[22],"rely":[23],"on":[24,45,115],"Automatic":[25],"Speech":[26],"Recognition":[27],"(ASR),":[28],"which":[29,49],"performs":[30],"suboptimally":[31],"due":[32],"to":[33,52,104,160],"its":[34],"broad":[35],"search":[36],"over":[37],"the":[38,87,90,125,156,161],"acoustic":[39],"space":[40],"without":[41],"keyword-specific":[42],"optimization,":[43],"or":[44],"KWS-specific":[46],"graphs,":[48],"are":[50],"complex":[51],"implement":[53],"and":[54,109,118,132,150],"maintain.":[55],"In":[56],"this":[57],"work,":[58],"we":[59,76,97],"propose":[60],"streaming":[62,127],"algorithm":[64,83],"enhanced":[65],"by":[66],"Cross-layer":[67],"Discrimination":[68],"Consistency":[69],"(CDC),":[70],"tailored":[71],"for":[72],"KWS.":[74],"Specifically,":[75],"introduce":[77],"streamlined":[79],"yet":[80],"effective":[81],"capable":[84],"of":[85,89,148,172],"detecting":[86],"start":[88],"at":[92],"any":[93],"arbitrary":[94],"position.":[95],"Furthermore,":[96],"leverage":[98],"discrimination":[99],"consistency":[100],"information":[101],"across":[102],"layers":[103],"better":[105],"differentiate":[106],"between":[107],"positive":[108],"false":[110,169],"alarm":[111,170],"samples.":[112],"Our":[113],"experiments":[114],"both":[116],"clean":[117],"noisy":[119],"Hey":[120],"Snips":[121],"datasets":[122],"show":[123],"that":[124],"proposed":[126],"strategy":[129],"outperforms":[130],"ASR-based":[131],"graph-based":[133,162],"baselines.":[135],"The":[136],"CDC-boosted":[137],"further":[139],"improves":[140],"performance,":[141],"yielding":[142],"an":[143],"average":[144],"absolute":[145],"recall":[146],"improvement":[147],"6.8%":[149],"46.3%":[152],"relative":[153],"reduction":[154],"miss":[157],"rate":[158,171],"compared":[159],"baseline,":[164],"with":[165],"very":[167],"low":[168],"0.05":[173],"per":[174],"hour.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}