{"id":"https://openalex.org/W1496120315","doi":"https://doi.org/10.1109/icassp.2015.7178970","title":"Query-by-example keyword spotting using long short-term memory networks","display_name":"Query-by-example keyword spotting using long short-term memory networks","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1496120315","doi":"https://doi.org/10.1109/icassp.2015.7178970","mag":"1496120315"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178970","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178970","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 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/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"]},{"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","Google, MTV"],"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":"Google, MTV","institution_ids":["https://openalex.org/I1291425158"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"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":"Tara N. Sainath","raw_affiliation_strings":["Google Inc., Mountain View, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA","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":157,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5236","last_page":"5240"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9979000091552734,"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":0.965866208076477},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8459235429763794},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.8171222805976868},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5607666373252869},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5250313878059387},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5124576687812805},{"id":"https://openalex.org/keywords/sliding-window-protocol","display_name":"Sliding window protocol","score":0.4877501130104065},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.48499366641044617},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4693875014781952},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.45023876428604126},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.4501681923866272},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.4212571978569031},{"id":"https://openalex.org/keywords/constant-false-alarm-rate","display_name":"Constant false alarm rate","score":0.4202796220779419},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3684656322002411},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.17093989253044128}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.965866208076477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8459235429763794},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.8171222805976868},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5607666373252869},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5250313878059387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5124576687812805},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.4877501130104065},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.48499366641044617},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4693875014781952},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.45023876428604126},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.4501681923866272},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.4212571978569031},{"id":"https://openalex.org/C77052588","wikidata":"https://www.wikidata.org/wiki/Q644307","display_name":"Constant false alarm rate","level":2,"score":0.4202796220779419},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3684656322002411},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.17093989253044128},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2015.7178970","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178970","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.684.8586","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.684.8586","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/icassp2015_myhotword.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7799999713897705,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W114193738","https://openalex.org/W121805954","https://openalex.org/W1544266773","https://openalex.org/W1582723958","https://openalex.org/W1734538896","https://openalex.org/W1999121090","https://openalex.org/W2000654171","https://openalex.org/W2015688877","https://openalex.org/W2034940213","https://openalex.org/W2048497537","https://openalex.org/W2056986588","https://openalex.org/W2059652594","https://openalex.org/W2089537772","https://openalex.org/W2110625382","https://openalex.org/W2122797512","https://openalex.org/W2126203737","https://openalex.org/W2137044559","https://openalex.org/W2140576685","https://openalex.org/W2143612262","https://openalex.org/W2145287260","https://openalex.org/W2155117693","https://openalex.org/W2156431836","https://openalex.org/W2160815625","https://openalex.org/W2168231600","https://openalex.org/W2171019095","https://openalex.org/W2296516251","https://openalex.org/W2398352857","https://openalex.org/W2612891210","https://openalex.org/W2916959077","https://openalex.org/W6604666349","https://openalex.org/W6608351678","https://openalex.org/W6632425017","https://openalex.org/W6634592987","https://openalex.org/W6665204316","https://openalex.org/W6673287344","https://openalex.org/W6680681483","https://openalex.org/W6683369307","https://openalex.org/W6684859321","https://openalex.org/W6697811694"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W3119978414","https://openalex.org/W2114097550","https://openalex.org/W2516975559","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W2000885660","https://openalex.org/W2088615611","https://openalex.org/W1969408022","https://openalex.org/W2117995638"],"abstract_inverted_index":{"We":[0,45],"present":[1],"a":[2,11,29,40,73,78,109,133],"novel":[3],"approach":[4],"to":[5,50,108],"query-by-example":[6],"keyword":[7,27,37,65,88],"spotting":[8],"(KWS)":[9],"using":[10,28],"long":[12],"short-term":[13],"memory":[14,135],"(LSTM)":[15],"recurrent":[16],"neural":[17],"network-based":[18],"feature":[19,31,70],"extractor.":[20],"In":[21],"our":[22,58],"approach,":[23],"we":[24,62,93],"represent":[25],"each":[26],"fixed-length":[30],"vector":[32,71,85],"obtained":[33],"by":[34,66],"running":[35],"the":[36,47,51,55,64,68,87,120,123],"audio":[38],"through":[39],"word-based":[41],"LSTM":[42,56],"acoustic":[43],"model.":[44],"use":[46],"activations":[48],"prior":[49],"softmax":[52],"layer":[53],"of":[54,125],"as":[57],"keyword-vector.":[59],"At":[60],"runtime,":[61],"detect":[63],"extracting":[67],"same":[69],"from":[72],"sliding":[74],"window":[75],"and":[76,86,140],"computing":[77],"simple":[79],"similarity":[80],"score":[81],"between":[82],"this":[83],"test":[84],"vector.":[89],"With":[90],"clean":[91],"speech,":[92],"achieve":[94],"86%":[95],"relative":[96],"false":[97,103],"rejection":[98],"rate":[99,105],"reduction":[100,121],"at":[101],"0.5%":[102],"alarm":[104],"when":[106],"compared":[107],"competitive":[110],"phoneme":[111],"posteriorgram":[112],"with":[113],"dynamic":[114],"time":[115],"warping":[116],"KWS":[117],"system,":[118],"while":[119],"in":[122],"presence":[124],"babble":[126],"noise":[127],"is":[128],"67%.":[129],"Our":[130],"system":[131],"has":[132],"small":[134],"footprint,":[136],"low":[137],"computational":[138],"cost,":[139],"high":[141],"precision,":[142],"making":[143],"it":[144],"suitable":[145],"for":[146],"on-device":[147],"applications.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":23},{"year":2018,"cited_by_count":23},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":14},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}