{"id":"https://openalex.org/W4392904395","doi":"https://doi.org/10.1109/icassp48485.2024.10446912","title":"Open-Vocabulary Keyword-Spotting with Adaptive Instance Normalization","display_name":"Open-Vocabulary Keyword-Spotting with Adaptive Instance Normalization","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904395","doi":"https://doi.org/10.1109/icassp48485.2024.10446912"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446912","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":"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/A5076537607","display_name":"Aviv Navon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aviv Navon","raw_affiliation_strings":["aiOla Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"aiOla Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040863261","display_name":"Aviv Shamsian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aviv Shamsian","raw_affiliation_strings":["aiOla Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"aiOla Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047865587","display_name":"Neta Glazer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Neta Glazer","raw_affiliation_strings":["aiOla Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"aiOla Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072070363","display_name":"Gill Hetz","orcid":"https://orcid.org/0000-0002-6477-7797"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gill Hetz","raw_affiliation_strings":["aiOla Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"aiOla Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008847407","display_name":"Joseph Keshet","orcid":"https://orcid.org/0000-0003-2332-5783"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joseph Keshet","raw_affiliation_strings":["aiOla Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"aiOla Research","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3601,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.9286526,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"11656","last_page":"11660"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9994999766349792,"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":0.9667385220527649},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8610221147537231},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7334255576133728},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.6741878986358643},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6322415471076965},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6139367818832397},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.609630823135376},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5822548866271973},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5599121451377869},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5197667479515076},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4220128059387207}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9667385220527649},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8610221147537231},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7334255576133728},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.6741878986358643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6322415471076965},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6139367818832397},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.609630823135376},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5822548866271973},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5599121451377869},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5197667479515076},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4220128059387207},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446912","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":[{"id":"https://metadata.un.org/sdg/4","score":0.49000000953674316,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2603777577","https://openalex.org/W2972613398","https://openalex.org/W3097018422","https://openalex.org/W3119308075","https://openalex.org/W3162022030","https://openalex.org/W3162273446","https://openalex.org/W3198035615","https://openalex.org/W4206567542","https://openalex.org/W4224916413","https://openalex.org/W4283767777","https://openalex.org/W4289243832","https://openalex.org/W4296069322","https://openalex.org/W4311000453","https://openalex.org/W4319862284","https://openalex.org/W4319862635","https://openalex.org/W4372260220","https://openalex.org/W4372346399","https://openalex.org/W4385822437","https://openalex.org/W4392902956","https://openalex.org/W6757022092","https://openalex.org/W6847363464"],"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":{"Open":[0],"vocabulary":[1],"keyword":[2,34,55,95],"spotting":[3,26,56,96],"is":[4,62],"a":[5,22,36,51,59,120],"crucial":[6],"and":[7,33,85,89,97],"challenging":[8,84],"task":[9],"in":[10,57],"automatic":[11],"speech":[12],"recognition":[13],"(ASR)":[14],"that":[15,111],"focuses":[16],"on":[17,108],"detecting":[18],"user-defined":[19],"keywords":[20],"within":[21],"spoken":[23],"utterance.":[24],"Keyword":[25],"methods":[27],"commonly":[28],"map":[29],"the":[30,75,103,115],"audio":[31],"utterance":[32],"into":[35],"joint":[37],"embedding":[38],"space":[39],"to":[40,64,73,125],"obtain":[41],"some":[42],"affinity":[43],"score.":[44],"In":[45],"this":[46],"work,":[47],"we":[48,101],"propose":[49],"AdaKWS,":[50],"novel":[52],"method":[53],"for":[54],"which":[58],"text":[60],"encoder":[61],"trained":[63],"output":[65],"keyword-conditioned":[66],"normalization":[67],"parameters.":[68],"These":[69],"parameters":[70],"are":[71],"used":[72],"process":[74],"auditory":[76],"input.":[77],"We":[78],"provide":[79],"an":[80],"extensive":[81],"evaluation":[82],"using":[83],"diverse":[86],"multi-lingual":[87],"benchmarks":[88],"show":[90],"significant":[91],"improvements":[92],"over":[93],"recent":[94],"ASR":[98],"baselines.":[99],"Furthermore,":[100],"study":[102],"effectiveness":[104],"of":[105],"our":[106],"approach":[107],"low-resource":[109],"languages":[110],"were":[112],"unseen":[113],"during":[114],"training.":[116],"The":[117],"results":[118],"demonstrate":[119],"substantial":[121],"performance":[122],"improvement":[123],"compared":[124],"baseline":[126],"methods.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
