{"id":"https://openalex.org/W4392902956","doi":"https://doi.org/10.1109/icassp48485.2024.10447547","title":"Flexible Keyword Spotting Based on Homogeneous Audio-Text Embedding","display_name":"Flexible Keyword Spotting Based on Homogeneous Audio-Text Embedding","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902956","doi":"https://doi.org/10.1109/icassp48485.2024.10447547"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447547","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447547","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5112980957","display_name":"Kumari Nishu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kumari Nishu","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115076654","display_name":"Minsik Cho","orcid":"https://orcid.org/0000-0003-0481-2682"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Minsik Cho","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049896100","display_name":"Paul R. Dixon","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Paul Dixon","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102495865","display_name":"Devang Naik","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Devang Naik","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210107260"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5050","last_page":"5054"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9973000288009644,"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/embedding","display_name":"Embedding","score":0.8452245593070984},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.8302711248397827},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.8084489703178406},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7897133231163025},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6093078255653381},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5745779871940613},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5558136105537415},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47330442070961},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.46516090631484985},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44593125581741333}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8452245593070984},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.8302711248397827},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8084489703178406},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7897133231163025},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6093078255653381},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5745779871940613},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5558136105537415},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47330442070961},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.46516090631484985},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44593125581741333},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447547","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447547","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":22,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2034940213","https://openalex.org/W2127141656","https://openalex.org/W2128160875","https://openalex.org/W2187089797","https://openalex.org/W2765122878","https://openalex.org/W2797583228","https://openalex.org/W2964187693","https://openalex.org/W2972592723","https://openalex.org/W2978017171","https://openalex.org/W3097777922","https://openalex.org/W3119913666","https://openalex.org/W4283767777","https://openalex.org/W4296069322","https://openalex.org/W4372260220","https://openalex.org/W4385245566","https://openalex.org/W4385822437","https://openalex.org/W6631190155","https://openalex.org/W6750665317","https://openalex.org/W6768851824","https://openalex.org/W6847210051"],"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":{"Spotting":[0],"user-defined/flexible":[1],"keywords":[2,48],"represented":[3],"in":[4,19],"text":[5,10,53,72,75,79],"frequently":[6],"uses":[7],"an":[8,16,20,51,90,117],"expensive":[9],"encoder":[11,18,54,76,101],"for":[12],"joint":[13],"analysis":[14],"with":[15,60,111,121],"audio":[17,61,100],"embedding":[21,91,119],"space,":[22],"which":[23,55],"can":[24],"suffer":[25],"from":[26,97,147,156],"heterogeneous":[27],"modality":[28],"representation":[29,59],"(i.e.,":[30],"large":[31],"mismatch)":[32],"and":[33,63,87,151],"increased":[34],"complexity.":[35],"In":[36],"this":[37],"work,":[38],"we":[39],"propose":[40],"a":[41,70,83],"novel":[42],"architecture":[43],"to":[44,80,89,115,149,158],"efficiently":[45],"detect":[46],"arbitrary":[47],"based":[49],"on":[50,102,135],"audio-compliant":[52],"inherently":[56],"has":[57],"homogeneous":[58],"embedding,":[62],"it":[64],"is":[65],"also":[66],"much":[67],"smaller":[68],"than":[69],"compatible":[71],"encoder.":[73],"Our":[74],"converts":[77],"the":[78,98,132,142],"phonemes":[81],"using":[82,92],"grapheme-to-phoneme":[84],"(G2P)":[85],"model,":[86],"then":[88],"representative":[93],"phoneme":[94],"vectors,":[95],"extracted":[96],"paired":[99],"rich":[103],"speech":[104],"datasets.":[105],"We":[106],"further":[107],"augment":[108],"our":[109,129],"method":[110],"confusable":[112],"keyword":[113],"generation":[114],"develop":[116],"audio-text":[118],"verifier":[120],"strong":[122],"discriminative":[123],"power.":[124],"Experimental":[125],"results":[126,134],"show":[127],"that":[128],"scheme":[130],"outperforms":[131],"state-of-the-art":[133],"Libriphrase":[136],"hard":[137],"dataset,":[138],"increasing":[139],"Area":[140],"Under":[141],"ROC":[143],"Curve":[144],"(AUC)":[145],"metric":[146,155],"84.21%":[148],"92.7%":[150],"reducing":[152],"Equal-Error-Rate":[153],"(EER)":[154],"23.36%":[157],"14.4%.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}