{"id":"https://openalex.org/W3015399080","doi":"https://doi.org/10.1109/icassp40776.2020.9053193","title":"Training Keyword Spotters with Limited and Synthesized Speech Data","display_name":"Training Keyword Spotters with Limited and Synthesized Speech Data","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015399080","doi":"https://doi.org/10.1109/icassp40776.2020.9053193","mag":"3015399080"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053193","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053193","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5083112512","display_name":"James Lin","orcid":"https://orcid.org/0000-0003-0841-3646"},"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":"James Lin","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034910585","display_name":"Kevin Kilgour","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":"Kevin Kilgour","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011258273","display_name":"Dominik Roblek","orcid":"https://orcid.org/0000-0002-2155-450X"},"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":"Dominik Roblek","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020362884","display_name":"Matthew Sharifi","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":"Matthew Sharifi","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":4.494,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.95738101,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7474","last_page":"7478"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9994000196456909,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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":0.9308514595031738},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8227818608283997},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.795401930809021},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6743403673171997},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.5968827605247498},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5851710438728333},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5036610960960388},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4747781455516815},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.47129786014556885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4634091556072235},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4244515895843506},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3268771767616272},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1437302827835083}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9308514595031738},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8227818608283997},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.795401930809021},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6743403673171997},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.5968827605247498},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5851710438728333},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5036610960960388},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4747781455516815},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.47129786014556885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4634091556072235},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4244515895843506},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3268771767616272},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1437302827835083},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053193","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053193","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2034940213","https://openalex.org/W2194775991","https://openalex.org/W2271840356","https://openalex.org/W2519091744","https://openalex.org/W2748659049","https://openalex.org/W2796346823","https://openalex.org/W2797583228","https://openalex.org/W2887528618","https://openalex.org/W2889511491","https://openalex.org/W2898727538","https://openalex.org/W2912937645","https://openalex.org/W2930364467","https://openalex.org/W2949382160","https://openalex.org/W2949650786","https://openalex.org/W2963628261","https://openalex.org/W2964243274","https://openalex.org/W2973226577","https://openalex.org/W3008480565","https://openalex.org/W6687483927","https://openalex.org/W6694517276","https://openalex.org/W6750665317","https://openalex.org/W6753500843","https://openalex.org/W6756385397"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W2000885660","https://openalex.org/W2117995638","https://openalex.org/W1969408022"],"abstract_inverted_index":{"With":[0],"the":[1,31,36,53,77,154],"rise":[2],"of":[3,21,30,45,55,66,71],"low":[4,80],"power":[5],"speech-enabled":[6],"devices,":[7],"there":[8],"is":[9,40,121],"a":[10,42,88,109,124,136],"growing":[11],"demand":[12],"to":[13,94,123,144,152],"quickly":[14],"produce":[15],"models":[16,65,74],"for":[17,98],"recognizing":[18],"arbitrary":[19],"sets":[20],"keywords.":[22],"As":[23],"with":[24],"many":[25],"machine":[26],"learning":[27],"tasks,":[28],"one":[29],"most":[32],"challenging":[33],"parts":[34],"in":[35,59],"model":[37,92,110,125,137],"creation":[38],"process":[39],"obtaining":[41],"sufficient":[43],"amount":[44],"training":[46,60,72],"data.":[47],"In":[48],"this":[49,103],"paper,":[50],"we":[51,86,106],"explore":[52],"effectiveness":[54],"synthesized":[56],"speech":[57,90,104,120,140],"data":[58],"small,":[61],"spoken":[62],"term":[63],"detection":[64],"around":[67],"400k":[68],"parameters.":[69],"Instead":[70],"such":[73,83],"directly":[75],"on":[76,117,127,147],"audio":[78],"or":[79],"level":[81],"features":[82,97],"as":[84],"MFCCs,":[85],"use":[87],"pre-trained":[89],"embedding":[91],"trained":[93,116,126,146],"extract":[95],"useful":[96],"keyword":[99],"spotting":[100],"models.":[101],"Using":[102],"embedding,":[105],"show":[107,134],"that":[108,135],"which":[111],"detects":[112],"10":[113],"keywords":[114],"when":[115],"only":[118],"synthetic":[119],"equivalent":[122],"over":[128,148],"500":[129],"real":[130,150],"examples.":[131],"We":[132],"also":[133],"without":[138],"our":[139],"embeddings":[141],"would":[142],"need":[143],"be":[145],"4000":[149],"examples":[151],"reach":[153],"same":[155],"accuracy.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":2}],"updated_date":"2026-08-13T07:04:57.449891","created_date":"2025-10-10T00:00:00"}