{"id":"https://openalex.org/W4372268294","doi":"https://doi.org/10.1109/icassp49357.2023.10095444","title":"Exploring Sequence-to-Sequence Transformer-Transducer Models for Keyword Spotting","display_name":"Exploring Sequence-to-Sequence Transformer-Transducer Models for Keyword Spotting","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372268294","doi":"https://doi.org/10.1109/icassp49357.2023.10095444"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Beltr\u00e1n Labrador","raw_affiliation_strings":["Universidad Aut&#x00F3;noma de Madrid,AUDIAS (Audio, Data Intelligence and Speech),Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Aut&#x00F3;noma de Madrid,AUDIAS (Audio, Data Intelligence and Speech),Spain","institution_ids":[]}]},{"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 LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","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 L\u00f3pez Moreno","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, 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 LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034473032","display_name":"Liam Fowl","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":"Liam Fowl","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","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 LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1086,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77132599,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"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/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":0.9991999864578247,"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":0.9129340648651123},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8081728219985962},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7133249044418335},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6477820873260498},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.5895229578018188},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5728026032447815},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.561423122882843},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5105704069137573},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4945509135723114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48252221941947937},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.41045624017715454},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.147286057472229},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10678213834762573}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9129340648651123},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8081728219985962},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7133249044418335},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6477820873260498},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.5895229578018188},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5728026032447815},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.561423122882843},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5105704069137573},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4945509135723114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48252221941947937},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.41045624017715454},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.147286057472229},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10678213834762573},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:repositorio.uam.es:10486/718748","is_oa":false,"landing_page_url":"http://hdl.handle.net/10486/718748","pdf_url":null,"source":{"id":"https://openalex.org/S4306400963","display_name":"Biblos-e Archivo (Universidad Aut\u00f3noma de Madrid)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63634437","host_organization_name":"Universidad Aut\u00f3noma de Madrid","host_organization_lineage":["https://openalex.org/I63634437"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/acceptedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1553469512","https://openalex.org/W1828163288","https://openalex.org/W2034940213","https://openalex.org/W2131342762","https://openalex.org/W2407023693","https://openalex.org/W2507319753","https://openalex.org/W2510945575","https://openalex.org/W2535838896","https://openalex.org/W2578392894","https://openalex.org/W2587529061","https://openalex.org/W2617258110","https://openalex.org/W2697044473","https://openalex.org/W2748659049","https://openalex.org/W2787752687","https://openalex.org/W2797759721","https://openalex.org/W2891722048","https://openalex.org/W2953219395","https://openalex.org/W2962707338","https://openalex.org/W2963747784","https://openalex.org/W2963977978","https://openalex.org/W3015273269","https://openalex.org/W3016010032","https://openalex.org/W3095697114","https://openalex.org/W3097777922","https://openalex.org/W3098773154","https://openalex.org/W3161525333","https://openalex.org/W3203417382","https://openalex.org/W4206567542","https://openalex.org/W4226316089","https://openalex.org/W4297687186","https://openalex.org/W4385245566","https://openalex.org/W6638749077","https://openalex.org/W6739901393","https://openalex.org/W6748315512"],"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/W2388033618","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W1969408022","https://openalex.org/W2000885660"],"abstract_inverted_index":{"In":[0],"this":[1,23],"paper,":[2],"we":[3,53,74],"present":[4],"a":[5,10,33,55,76,103],"novel":[6],"approach":[7,66,93,131],"to":[8,15,41,63],"adapt":[9],"sequence-to-sequence":[11,120],"Transformer-Transducer":[12],"ASR":[13,96],"system":[14,40],"the":[16,26,29,39,43,70,83,115,126,134],"keyword":[17,27,78,105],"spotting":[18,79,106],"(KWS)":[19],"task.":[20,72],"We":[21,89],"achieve":[22],"by":[24,59,81],"replacing":[25],"in":[28,46],"text":[30],"transcription":[31],"with":[32,102,125],"special":[34],"token":[35,45],"<kw>":[36,44],"and":[37,117],"training":[38,87],"detect":[42],"an":[47],"audio":[48],"stream.":[49],"At":[50],"inference":[51],"time,":[52],"create":[54],"decision":[56],"function":[57],"inspired":[58],"conventional":[60,104,127],"KWS":[61,71,98,128],"approaches,":[62],"make":[64],"our":[65,92,108,130],"more":[67],"suitable":[68],"for":[69],"Furthermore,":[73],"introduce":[75],"specific":[77],"loss":[80],"adapting":[82],"sequence-discriminative":[84],"Minimum":[85],"Bayes-Risk":[86],"technique.":[88],"find":[90],"that":[91],"significantly":[94],"outperforms":[95],"based":[97],"systems.":[99],"When":[100],"compared":[101],"system,":[107,129],"proposal":[109],"has":[110],"similar":[111],"performance":[112,135],"while":[113],"bringing":[114],"advantages":[116],"flexibility":[118],"of":[119],"training.":[121],"Additionally,":[122],"when":[123],"combined":[124],"can":[132],"improve":[133],"at":[136],"any":[137],"operation":[138],"point.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2023-05-07T00:00:00"}