{"id":"https://openalex.org/W2034940213","doi":"https://doi.org/10.1109/icassp.2014.6854370","title":"Small-footprint keyword spotting using deep neural networks","display_name":"Small-footprint keyword spotting using deep neural networks","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2034940213","doi":"https://doi.org/10.1109/icassp.2014.6854370","mag":"2034940213"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854370","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854370","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 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/A5081371370","display_name":"Guoguo Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guoguo Chen","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD","Center for Language & Speech Process., Johns Hopkins Univ., Baltimore, MD, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language & Speech Process., Johns Hopkins Univ., Baltimore, MD, USA#TAB#","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090570382","display_name":"Carolina Parada","orcid":"https://orcid.org/0009-0000-7772-4646"},"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":"Carolina Parada","raw_affiliation_strings":["Google Inc., Mountain View, CA","Google Inc., Mountain View, CA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., Mountain View, CA USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071956319","display_name":"Georg Heigold","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":"Georg Heigold","raw_affiliation_strings":["Google Inc., Mountain View, CA","Google Inc., Mountain View, CA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., Mountain View, CA USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":570,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4087","last_page":"4091"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","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/T11550","display_name":"Text and Document Classification Technologies","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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9970999956130981,"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/T10028","display_name":"Topic Modeling","score":0.9968000054359436,"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":0.9692398905754089},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8582565784454346},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.7793211936950684},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.6875306367874146},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.661772608757019},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6526146531105042},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5890094041824341},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5689535737037659},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.5576789975166321},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4523102939128876},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4258689284324646},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4166698455810547},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38343745470046997},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3696121275424957},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.320778489112854}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9692398905754089},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8582565784454346},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.7793211936950684},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.6875306367874146},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.661772608757019},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6526146531105042},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5890094041824341},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5689535737037659},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.5576789975166321},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4523102939128876},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4258689284324646},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4166698455810547},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38343745470046997},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3696121275424957},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.320778489112854},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2014.6854370","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854370","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.684.3006","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.684.3006","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://static.googleusercontent.com/media/research.google.com/en/us/pubs/archive/42537.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.685.1328","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.685.1328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.clsp.jhu.edu/%7Eguoguo/papers/icassp2014_dnn_hotword.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W114193738","https://openalex.org/W1544266773","https://openalex.org/W1553469512","https://openalex.org/W1582723958","https://openalex.org/W1734538896","https://openalex.org/W1978660892","https://openalex.org/W1999121090","https://openalex.org/W2015688877","https://openalex.org/W2035424729","https://openalex.org/W2040226630","https://openalex.org/W2048497537","https://openalex.org/W2056986588","https://openalex.org/W2085697202","https://openalex.org/W2119690257","https://openalex.org/W2120480077","https://openalex.org/W2122797512","https://openalex.org/W2125964738","https://openalex.org/W2151244813","https://openalex.org/W2156431836","https://openalex.org/W2168231600","https://openalex.org/W2253807446","https://openalex.org/W2296516251","https://openalex.org/W2296748324","https://openalex.org/W2913340405","https://openalex.org/W2914746235","https://openalex.org/W4206606553","https://openalex.org/W6604666349","https://openalex.org/W6632425017","https://openalex.org/W6634592987","https://openalex.org/W6664384591","https://openalex.org/W6678242812","https://openalex.org/W6679053740","https://openalex.org/W6684859321"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W3119978414","https://openalex.org/W2114097550","https://openalex.org/W2545741539","https://openalex.org/W2516975559","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W2000885660","https://openalex.org/W1969408022","https://openalex.org/W2034940213"],"abstract_inverted_index":{"Our":[0],"application":[1],"requires":[2],"a":[3,8,24,51,56,70],"keyword":[4],"spotting":[5],"system":[6],"with":[7,67],"small":[9],"memory":[10],"footprint,":[11],"low":[12],"computational":[13],"cost,":[14],"and":[15],"high":[16],"precision.":[17],"To":[18],"meet":[19],"these":[20],"requirements,":[21],"we":[22],"propose":[23],"simple":[25],"approach":[26],"based":[27],"on":[28],"deep":[29,33],"neural":[30,34],"networks.":[31],"A":[32],"network":[35],"is":[36],"trained":[37],"to":[38,69],"directly":[39],"predict":[40],"the":[41,47,79],"keyword(s)":[42,48],"or":[43],"subword":[44],"units":[45],"of":[46,81],"followed":[49],"by":[50],"posterior":[52],"handling":[53],"method":[54],"producing":[55],"final":[57],"confidence":[58],"score.":[59],"Keyword":[60],"recognition":[61],"results":[62],"achieve":[63],"45%":[64],"relative":[65,86],"improvement":[66],"respect":[68],"competitive":[71],"Hidden":[72],"Markov":[73],"Model-based":[74],"system,":[75],"while":[76],"performance":[77],"in":[78],"presence":[80],"babble":[82],"noise":[83],"shows":[84],"39%":[85],"improvement.":[87]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":28},{"year":2024,"cited_by_count":35},{"year":2023,"cited_by_count":44},{"year":2022,"cited_by_count":65},{"year":2021,"cited_by_count":100},{"year":2020,"cited_by_count":77},{"year":2019,"cited_by_count":65},{"year":2018,"cited_by_count":60},{"year":2017,"cited_by_count":39},{"year":2016,"cited_by_count":28},{"year":2015,"cited_by_count":20}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}