{"id":"https://openalex.org/W4408354069","doi":"https://doi.org/10.1109/icassp49660.2025.10890730","title":"Personalizing Keyword Spotting with Speaker Information","display_name":"Personalizing Keyword Spotting with Speaker Information","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354069","doi":"https://doi.org/10.1109/icassp49660.2025.10890730"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890730","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890730","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":"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/A5055196565","display_name":"Beltr\u00e1n Labrador","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Beltr\u00e1n Labrador","raw_affiliation_strings":["Google,Zurich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,Zurich,Switzerland","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053897661","display_name":"Pai Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pai Zhu","raw_affiliation_strings":["Google,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,New York,USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078020198","display_name":"Guanlong Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guanlong Zhao","raw_affiliation_strings":["Google,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,New York,USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072807660","display_name":"Angelo Scorza Scarpati","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Angelo Scorza Scarpati","raw_affiliation_strings":["Google,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,New York,USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418247","display_name":"Quan Wang","orcid":"https://orcid.org/0000-0001-6913-8604"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Quan Wang","raw_affiliation_strings":["Google,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,New York,USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063156730","display_name":"Alicia Lozano-D\u00edez","orcid":"https://orcid.org/0000-0002-5918-8568"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alicia Lozano-Diez","raw_affiliation_strings":["Universidad Autónoma de Madrid,Audias, Escuela Politécnica Superior,Madrid,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Autónoma de Madrid,Audias, Escuela Politécnica Superior,Madrid,Spain","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050898122","display_name":"Ignacio L\u00f3pez Moreno","orcid":"https://orcid.org/0000-0002-0900-3473"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ignacio Lopez-Moreno","raw_affiliation_strings":["Google,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,New York,USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7588,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85584521,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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":0.9958999752998352,"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":0.9958999752998352,"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":0.951657772064209},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7823835015296936},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.6213955283164978},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43981313705444336},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3614981770515442},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3347780406475067}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.951657772064209},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7823835015296936},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.6213955283164978},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43981313705444336},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3614981770515442},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3347780406475067}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890730","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890730","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2034940213","https://openalex.org/W2121415728","https://openalex.org/W2295405790","https://openalex.org/W2404620314","https://openalex.org/W2407023693","https://openalex.org/W2587529061","https://openalex.org/W2617258110","https://openalex.org/W2748659049","https://openalex.org/W2760103357","https://openalex.org/W2787752687","https://openalex.org/W2890964092","https://openalex.org/W2913340405","https://openalex.org/W2962788625","https://openalex.org/W2963977978","https://openalex.org/W2972384212","https://openalex.org/W2973062255","https://openalex.org/W3015273269","https://openalex.org/W3024085360","https://openalex.org/W3097777922","https://openalex.org/W3161038873","https://openalex.org/W3197845638","https://openalex.org/W3197949759","https://openalex.org/W4206567542","https://openalex.org/W4221141648","https://openalex.org/W4223655162","https://openalex.org/W4283727191","https://openalex.org/W4297841331","https://openalex.org/W4297841921","https://openalex.org/W4372268294","https://openalex.org/W4375869070","https://openalex.org/W4399393122","https://openalex.org/W6846909052"],"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":{"Keyword":[0],"spotting":[1,32],"systems":[2,60,83],"often":[3],"struggle":[4],"to":[5,7,44,61,115],"generalize":[6],"a":[8,23,38,85,92,127,137,148],"diverse":[9,86],"population":[10],"with":[11,136],"various":[12],"accents":[13],"and":[14,50,56,65,77,113,142],"age":[15],"groups.":[16,120],"To":[17],"address":[18],"this":[19,70],"challenge,":[20],"we":[21,66],"propose":[22],"novel":[24],"approach":[25,90,124],"that":[26,41],"integrates":[27],"speaker":[28,58,63,119],"information":[29,71],"into":[30],"keyword":[31],"using":[33],"Feature-wise":[34],"Linear":[35],"Modulation":[36],"(FiLM),":[37],"recent":[39],"method":[40],"allows":[42],"models":[43],"learn":[45],"from":[46,72],"different":[47],"data":[48],"inputs":[49],"features.":[51],"We":[52],"explore":[53],"both":[54,73],"Text-Dependent":[55],"Text-Independent":[57],"recognition":[59],"extract":[62],"information,":[64],"experiment":[67],"on":[68,84,97,140],"extracting":[69],"the":[74,132],"input":[75],"audio":[76],"pre-enrolled":[78],"user":[79],"audio.":[80],"Evaluating":[81],"our":[82,88,122],"dataset,":[87],"primary":[89],"yields":[91],"notable":[93],"2.6%":[94],"relative":[95],"improvement":[96],"Equal":[98],"Error":[99],"Rate":[100],"overall,":[101],"particularly":[102],"improving":[103],"performance":[104],"by":[105],"5.9%":[106],"for":[107,117,151],"children":[108],"under":[109],"12":[110],"years":[111],"old":[112],"up":[114],"24%":[116],"underrepresented":[118],"Moreover,":[121],"proposed":[123],"only":[125],"requires":[126],"small":[128],"1%":[129],"increase":[130],"in":[131],"number":[133],"of":[134],"parameters,":[135],"minimum":[138],"impact":[139],"latency":[141],"computational":[143],"cost,":[144],"which":[145],"makes":[146],"it":[147],"practical":[149],"solution":[150],"real-world":[152],"applications.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}