{"id":"https://openalex.org/W1990900815","doi":"https://doi.org/10.1109/icassp.2014.6854986","title":"Feature fusion for high-accuracy keyword spotting","display_name":"Feature fusion for high-accuracy keyword spotting","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W1990900815","doi":"https://doi.org/10.1109/icassp.2014.6854986","mag":"1990900815"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854986","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854986","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":"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/A5091201226","display_name":"Vikramjit Mitra","orcid":"https://orcid.org/0000-0002-2721-3976"},"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":true,"raw_author_name":"Vikramjit Mitra","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Menlo Park, CA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Menlo Park, CA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","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":["Speech Technology and Research Laboratory, SRI International, Menlo Park, CA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Menlo Park, CA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112857367","display_name":"Horacio Franco","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":"Horacio Franco","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Menlo Park, CA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Menlo Park, CA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060715364","display_name":"Dimitra Vergyri","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":"Dimitra Vergyri","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Menlo Park, CA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Menlo Park, CA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101648572","display_name":"Yun Lei","orcid":"https://orcid.org/0000-0003-4572-6078"},"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":"Yun Lei","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Menlo Park, CA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Menlo Park, CA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025265147","display_name":"Martin Graciarena","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":"Martin Graciarena","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Menlo Park, CA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Menlo Park, CA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yik-Cheung Tam","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":"Yik-Cheung Tam","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Menlo Park, CA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Menlo Park, CA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101494873","display_name":"Jing Zheng","orcid":"https://orcid.org/0000-0003-2724-8471"},"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":"Jing Zheng","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Menlo Park, CA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Menlo Park, CA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5091201226"],"corresponding_institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"],"apc_list":null,"apc_paid":null,"fwci":1.6914,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.87172,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"11","issue":null,"first_page":"7143","last_page":"7147"},"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/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/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"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":0.9415106773376465},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.813031792640686},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6312540769577026},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5899909138679504},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5601320862770081},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5511608719825745},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.537667989730835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5134811997413635},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5027182102203369},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.500882625579834},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4708064794540405},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4612096846103668},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4542144536972046},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06781858205795288}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9415106773376465},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.813031792640686},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6312540769577026},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5899909138679504},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5601320862770081},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5511608719825745},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.537667989730835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5134811997413635},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5027182102203369},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.500882625579834},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4708064794540405},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4612096846103668},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4542144536972046},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06781858205795288},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2014.6854986","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854986","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:10.1.1.465.7294","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.465.7294","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/ICASSP14_fusedfeat_KWS_mitra_v5_embedded.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1631260214","https://openalex.org/W1860566644","https://openalex.org/W1981730446","https://openalex.org/W1992810169","https://openalex.org/W2028956843","https://openalex.org/W2097978681","https://openalex.org/W2108072369","https://openalex.org/W2108767768","https://openalex.org/W2137075158","https://openalex.org/W2140979961","https://openalex.org/W2145094598","https://openalex.org/W2151244813","https://openalex.org/W2295098554","https://openalex.org/W2398177287","https://openalex.org/W2404382759","https://openalex.org/W2405666970","https://openalex.org/W2887979278","https://openalex.org/W2964076070","https://openalex.org/W2997574889","https://openalex.org/W6636811518","https://openalex.org/W6674334065","https://openalex.org/W6681096077","https://openalex.org/W6697089127","https://openalex.org/W6712709601","https://openalex.org/W6713419400","https://openalex.org/W6713568955","https://openalex.org/W6753916174"],"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/W1989658893"],"abstract_inverted_index":{"This":[0,110],"paper":[1],"assesses":[2],"the":[3,50,62,94,105,129],"role":[4],"of":[5,28,64,87,96,107,117,145,188,204],"robust":[6,65],"acoustic":[7,30,66],"features":[8,31,67,119,131,167],"in":[9,35,38,198],"spoken":[10,56],"term":[11,57],"detection":[12],"(a.k.a":[13],"keyword":[14],"spotting":[15],"-":[16],"KWS)":[17],"under":[18],"heavily":[19],"degraded":[20],"channel":[21],"and":[22,37,173,190],"noise":[23],"corrupted":[24],"conditions.":[25],"A":[26],"number":[27,95,106,116],"noise-robust":[29],"were":[32],"used,":[33],"both":[34],"isolation":[36],"combination,":[39],"to":[40,73,123,160,202],"train":[41,124],"large":[42],"vocabulary":[43],"continuous":[44],"speech":[45],"recognition":[46],"(LVCSR)":[47],"systems,":[48],"with":[49,71,135,170],"resulting":[51],"word":[52],"lattices":[53],"used":[54],"for":[55],"detection.":[58],"Results":[59,148],"indicate":[60],"that":[61,85,98,113,153,186],"use":[63],"improved":[68,158],"KWS":[69,91,154,199],"performance":[70,155,200],"respect":[72],"a":[74,115,142],"highly":[75],"optimized":[76],"state-of-the":[77],"art":[78],"baseline":[79],"system.":[80],"It":[81],"has":[82],"been":[83],"shown":[84],"fusion":[86,138,187,203],"multiple":[88,166,177],"systems":[89,97,126,164,179,194],"improve":[90],"performance,":[92],"however":[93],"can":[99,156],"be":[100,157],"trained":[101],"is":[102,121],"constrained":[103],"by":[104,127,132],"frontend":[108,118,130],"features.":[109],"work":[111,151,184],"shows":[112,185],"given":[114],"it":[120],"possible":[122],"several":[125],"using":[128],"themselves":[133],"along":[134],"different":[136],"feature":[137,162,192],"techniques,":[139],"which":[140],"provides":[141],"richer":[143],"set":[144],"individual":[146,161],"systems.":[147,207],"from":[149],"this":[150,183],"show":[152],"compared":[159,201],"based":[163,206],"when":[165,176],"are":[168,180],"fused":[169,189],"one":[171],"another":[172],"even":[174],"further":[175],"such":[178],"combined.":[181],"Finally":[182],"single":[191],"bases":[193],"provide":[195],"significant":[196],"improvement":[197],"singlefeature":[205]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}