{"id":"https://openalex.org/W2936963649","doi":"https://doi.org/10.1109/icassp.2019.8683265","title":"Semi-supervised and Population Based Training for Voice Commands Recognition","display_name":"Semi-supervised and Population Based Training for Voice Commands Recognition","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2936963649","doi":"https://doi.org/10.1109/icassp.2019.8683265","mag":"2936963649"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683265","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683265","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5111953908","display_name":"O\u011fuz H. Elibol","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Oguz H. Elibol","raw_affiliation_strings":["Intel AI Lab, Santa Clara, CA"],"affiliations":[{"raw_affiliation_string":"Intel AI Lab, Santa Clara, CA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026246923","display_name":"Gokce Keskin","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gokce Keskin","raw_affiliation_strings":["Intel AI Lab, Santa Clara, CA"],"affiliations":[{"raw_affiliation_string":"Intel AI Lab, Santa Clara, CA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019478468","display_name":"Anil Thomas","orcid":"https://orcid.org/0000-0002-0774-2512"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anil Thomas","raw_affiliation_strings":["Intel AI Lab, Santa Clara, CA"],"affiliations":[{"raw_affiliation_string":"Intel AI Lab, Santa Clara, CA","institution_ids":["https://openalex.org/I1343180700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5111953908"],"corresponding_institution_ids":["https://openalex.org/I1343180700"],"apc_list":null,"apc_paid":null,"fwci":0.28,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63812946,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"6371","last_page":"6375"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9959999918937683,"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/T12031","display_name":"Speech and dialogue systems","score":0.9959999918937683,"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/computer-science","display_name":"Computer science","score":0.8041068315505981},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5999844074249268},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5992714762687683},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5786799788475037},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5516284704208374},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5180147290229797},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.5130816698074341},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.41413068771362305},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3477088510990143},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3277437388896942}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8041068315505981},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5999844074249268},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5992714762687683},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5786799788475037},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5516284704208374},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5180147290229797},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5130816698074341},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.41413068771362305},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3477088510990143},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3277437388896942},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683265","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683265","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2091432990","https://openalex.org/W2194775991","https://openalex.org/W2519091744","https://openalex.org/W2592691248","https://openalex.org/W2770298516","https://openalex.org/W2783538964","https://openalex.org/W2787712888","https://openalex.org/W2797583228","https://openalex.org/W2953070460","https://openalex.org/W3022863654","https://openalex.org/W4289436996","https://openalex.org/W4394662461","https://openalex.org/W6733814495"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4224009465","https://openalex.org/W4306674287","https://openalex.org/W4286629047","https://openalex.org/W4205958290","https://openalex.org/W4384212932","https://openalex.org/W4390590544","https://openalex.org/W2096195258","https://openalex.org/W2389546251","https://openalex.org/W2990460313"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,61,105],"rapid":[3],"design":[4],"methodology":[5],"that":[6],"combines":[7],"automated":[8],"hyper-parameter":[9,45,84],"tuning":[10],"with":[11,60],"semi-supervised":[12,64],"training":[13,89],"to":[14,33,72,103],"build":[15],"highly":[16],"accurate":[17],"and":[18,36,90],"robust":[19],"models":[20],"for":[21,47],"voice":[22],"commands":[23],"classification.":[24],"Proposed":[25],"approach":[26],"allows":[27],"quick":[28],"evaluation":[29],"of":[30,39,57],"network":[31,49],"architectures":[32],"fit":[34],"performance":[35],"power":[37],"constraints":[38],"available":[40],"hardware,":[41],"while":[42],"ensuring":[43],"good":[44],"choices":[46],"each":[48],"in":[50,74,95],"real-world":[51],"scenarios.":[52],"Leveraging":[53],"the":[54,75,83,96],"vast":[55],"amount":[56],"unlabeled":[58],"data":[59],"student/teacher":[62],"based":[63,88],"method,":[65],"classification":[66],"accuracy":[67],"is":[68],"improved":[69],"from":[70],"84%":[71],"94%":[73],"validation":[76],"set.":[77],"For":[78],"model":[79,94],"optimization,":[80],"we":[81],"explore":[82],"space":[85],"through":[86],"population":[87],"obtain":[91],"an":[92],"optimized":[93],"same":[97],"time":[98],"frame":[99],"as":[100],"it":[101],"takes":[102],"train":[104],"single":[106],"model.":[107]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}