{"id":"https://openalex.org/W4401506990","doi":"https://doi.org/10.1109/lsp.2024.3442092","title":"Bridging the Gap Between Audio and Text Using Parallel-Attention for User-Defined Keyword Spotting","display_name":"Bridging the Gap Between Audio and Text Using Parallel-Attention for User-Defined Keyword Spotting","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401506990","doi":"https://doi.org/10.1109/lsp.2024.3442092"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2024.3442092","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/lsp.2024.3442092","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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":"https://openalex.org/A5050764943","display_name":"Youkyum Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Youkyum Kim","raw_affiliation_strings":["School of Electric Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0009-0001-4942-1901","affiliations":[{"raw_affiliation_string":"School of Electric Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jaemin Jung","orcid":"https://orcid.org/0009-0004-4072-8474"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaemin Jung","raw_affiliation_strings":["School of Electric Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0009-0004-4072-8474","affiliations":[{"raw_affiliation_string":"School of Electric Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100740584","display_name":"Jihwan Park","orcid":"https://orcid.org/0009-0007-2223-7278"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jihwan Park","raw_affiliation_strings":["42dot Inc., Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"42dot Inc., Seoul, South Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053784244","display_name":"Byeong-Yeol Kim","orcid":"https://orcid.org/0000-0001-6019-5047"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Byeong-Yeol Kim","raw_affiliation_strings":["42dot Inc., Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"42dot Inc., Seoul, South Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["School of Electric Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-7741-7275","affiliations":[{"raw_affiliation_string":"School of Electric Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5050764943"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.3311,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.64619326,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"31","issue":null,"first_page":"2100","last_page":"2104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9957000017166138,"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":0.9957000017166138,"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/T11309","display_name":"Music and Audio Processing","score":0.9732000231742859,"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":0.9617881774902344},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.8490080833435059},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8202931880950928},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.7374125123023987},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5051291584968567},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33427953720092773},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3278229832649231},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32638004422187805},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08177539706230164}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9617881774902344},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.8490080833435059},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8202931880950928},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.7374125123023987},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5051291584968567},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33427953720092773},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3278229832649231},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32638004422187805},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08177539706230164}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2024.3442092","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/lsp.2024.3442092","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1496120315","https://openalex.org/W2034940213","https://openalex.org/W2127141656","https://openalex.org/W2219249508","https://openalex.org/W2797583228","https://openalex.org/W2950635152","https://openalex.org/W2964187693","https://openalex.org/W2969991587","https://openalex.org/W3008790380","https://openalex.org/W3015399080","https://openalex.org/W3034275286","https://openalex.org/W3046052470","https://openalex.org/W3097777922","https://openalex.org/W3144247233","https://openalex.org/W3148564648","https://openalex.org/W3160183718","https://openalex.org/W3162273446","https://openalex.org/W3174758275","https://openalex.org/W3198035615","https://openalex.org/W4221154336","https://openalex.org/W4283767777","https://openalex.org/W4312497610","https://openalex.org/W4372260220","https://openalex.org/W4372267150","https://openalex.org/W4382466643","https://openalex.org/W4385822437","https://openalex.org/W4385823483","https://openalex.org/W4392902956","https://openalex.org/W6631190155","https://openalex.org/W6636915900","https://openalex.org/W6688816777","https://openalex.org/W6739901393","https://openalex.org/W6750665317","https://openalex.org/W6796730497"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W3119978414","https://openalex.org/W4286904253","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2117995638"],"abstract_inverted_index":{"This":[0],"letter":[1],"proposes":[2],"a":[3,48,65],"novel":[4],"user-defined":[5],"keyword":[6],"spotting":[7],"framework":[8],"that":[9,70,84],"accurately":[10],"detects":[11],"audio":[12,19,76],"keywords":[13],"based":[14],"on":[15,91],"text":[16,78],"enrollment.":[17],"Since":[18],"data":[20,104],"possesses":[21],"additional":[22],"acoustic":[23],"information":[24,54],"compared":[25],"to":[26,51],"text,":[27],"there":[28],"are":[29],"discrepancies":[30],"between":[31,75],"these":[32],"two":[33,60],"modalities.":[34,61],"To":[35],"address":[36],"this":[37],"challenge,":[38],"we":[39],"present":[40],"ParallelKWS,":[41],"which":[42],"utilises":[43],"self-":[44],"and":[45,57,77,98],"cross-attention":[46],"in":[47,95,109],"parallel":[49],"architecture":[50],"effectively":[52],"capture":[53],"both":[55,96],"within":[56],"across":[58],"the":[59,72,106],"We":[62],"further":[63],"propose":[64],"phoneme":[66],"duration-based":[67],"alignment":[68],"loss":[69],"enforces":[71],"sequential":[73],"correspondence":[74],"features.":[79],"Extensive":[80],"experimental":[81],"results":[82],"demonstrate":[83],"our":[85],"proposed":[86],"method":[87],"achieves":[88],"state-of-the-art":[89],"performance":[90],"several":[92],"benchmark":[93],"datasets":[94],"seen":[97],"unseen":[99],"domains,":[100],"without":[101],"incorporating":[102],"extra":[103],"beyond":[105],"dataset":[107],"used":[108],"previous":[110],"studies.":[111]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}