{"id":"https://openalex.org/W1986840384","doi":"https://doi.org/10.1109/icassp.2013.6639277","title":"Rich system combination for keyword spotting in noisy and acoustically heterogeneous audio streams","display_name":"Rich system combination for keyword spotting in noisy and acoustically heterogeneous audio streams","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W1986840384","doi":"https://doi.org/10.1109/icassp.2013.6639277","mag":"1986840384"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639277","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639277","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5076998541","display_name":"Murat Akbacak","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Murat Akbacak","raw_affiliation_strings":["Microsoft, Sunnyvale, CA, USA","Microsoft, Sunnyvale, CA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Sunnyvale, CA, USA#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lukas Burget","raw_affiliation_strings":["Brno University of Technology, Czech Republic","Brno University of Technology. Brno, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Czech Republic","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Brno University of Technology. Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396385","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0003-1707-0163"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen Wang","raw_affiliation_strings":["SRI International, Menlo Park, CA, USA","SRI Int., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058481276","display_name":"Julien van Hout","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julien van Hout","raw_affiliation_strings":["SRI International, Menlo Park, CA, USA","SRI Int., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8267","last_page":"8271"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.8873333930969238},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8663551807403564},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7392071485519409},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.6698505282402039},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5496535897254944},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5413650274276733},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5117430686950684},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4873236119747162},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.44103696942329407},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38152873516082764},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3734966218471527},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37199753522872925},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2141517996788025},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09428581595420837}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8873333930969238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8663551807403564},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7392071485519409},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.6698505282402039},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5496535897254944},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5413650274276733},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5117430686950684},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4873236119747162},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44103696942329407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38152873516082764},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3734966218471527},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37199753522872925},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2141517996788025},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09428581595420837},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6639277","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639277","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.379.8540","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.379.8540","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-speech.sri.com/papers/icassp2013-keyword-spotting.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.49000000953674316}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320327708","display_name":"University of Texas at Dallas","ror":"https://ror.org/049emcs32"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W23025778","https://openalex.org/W61569622","https://openalex.org/W210770835","https://openalex.org/W1524333225","https://openalex.org/W1981706894","https://openalex.org/W1998474788","https://openalex.org/W2023238506","https://openalex.org/W2094709280","https://openalex.org/W2104212264","https://openalex.org/W2110406951","https://openalex.org/W2140979961","https://openalex.org/W2158195707","https://openalex.org/W2168119002","https://openalex.org/W2394840413","https://openalex.org/W2397840928","https://openalex.org/W2402698866","https://openalex.org/W2887979278","https://openalex.org/W2888441252","https://openalex.org/W6600906190","https://openalex.org/W6602504224","https://openalex.org/W6608545824","https://openalex.org/W6713204639","https://openalex.org/W6753916174","https://openalex.org/W6754415462"],"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/W2149998531"],"abstract_inverted_index":{"We":[0,152],"address":[1],"the":[2,54,108,119],"problem":[3],"of":[4,23,56,121,174],"retrieving":[5],"spoken":[6],"information":[7,116],"from":[8,100],"noisy":[9],"and":[10,20,38,40,64,79,90,143,194],"heterogeneous":[11,41],"audio":[12,88],"archives":[13],"using":[14,111],"system":[15,60,105,131,133,166],"combination":[16,106,132,167],"with":[17,75],"a":[18,57,112,138,158],"rich":[19,165],"diverse":[21,65],"set":[22],"noise-robust":[24],"modules.":[25],"Audio":[26],"search":[27,91,144],"applications":[28],"so":[29],"far":[30],"have":[31],"focused":[32],"on":[33,137,169],"constrained":[34],"domains":[35],"or":[36,43],"genres":[37],"not-so-noisy":[39],"acoustic":[42,123],"channel":[44,66,184,196],"conditions.":[45],"In":[46],"this":[47],"paper,":[48],"our":[49,163],"focus":[50],"is":[51,127,135,145],"to":[52,129],"improve":[53],"accuracy":[55],"keyword":[58,98,149],"spotting":[59,150],"in":[61,73,147,155],"highly":[62,182],"degraded":[63,183],"conditions":[67],"by":[68,161],"employing":[69,162],"multiple":[70],"recognition":[71],"systems":[72],"parallel":[74],"different":[76,85,101,195],"robust":[77],"frontends":[78],"modeling":[80],"choices,":[81],"as":[82,84,118,189,191],"well":[83],"representations":[86],"during":[87],"indexing":[89,142],"(words":[92],"vs.":[93],"subword":[94],"units).":[95],"After":[96],"aligning":[97],"hits":[99],"systems,":[102],"we":[103],"employ":[104],"at":[107,157],"score":[109],"level":[110],"logistic-regression-based":[113],"classifier.":[114],"Side":[115],"such":[117],"output":[120],"an":[122],"condition":[124],"identification":[125],"module":[126],"used":[128,146],"guide":[130],"that":[134,180],"trained":[136],"held-out":[139],"dataset.":[140],"Lattice-based":[141],"all":[148],"systems.":[151],"present":[153],"improvements":[154],"probability-miss":[156],"fixed":[159],"probability-false-alarm":[160],"proposed":[164],"approach":[168],"DARPA":[170],"Robust":[171],"Automatic":[172],"Transcription":[173],"Speech":[175],"(RATS)":[176],"Phase-I":[177],"evaluation":[178],"data":[179],"contains":[181],"recordings":[185],"(signal-to-noise":[186],"ratio":[187],"levels":[188],"low":[190],"0":[192],"dB)":[193],"characteristics.":[197]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}