{"id":"https://openalex.org/W1567711539","doi":"https://doi.org/10.21437/interspeech.2007-328","title":"Learning the inter-frame distance for discriminative template-based keyword detection","display_name":"Learning the inter-frame distance for discriminative template-based keyword detection","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W1567711539","doi":"https://doi.org/10.21437/interspeech.2007-328","mag":"1567711539"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-328","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://publications.idiap.ch/downloads/reports/2007/grangier_eurospeech07.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065912572","display_name":"David Grangier","orcid":"https://orcid.org/0000-0002-8847-9532"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"David Grangier","raw_affiliation_strings":["IDIAP research institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017529415","display_name":"Samy Bengio","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":"Samy Bengio","raw_affiliation_strings":["Google\u2020#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google\u2020#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.06142578,"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":"902","last_page":"905"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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":0.9998000264167786,"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":0.9997000098228455,"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/discriminative-model","display_name":"Discriminative model","score":0.8763937950134277},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7445746660232544},{"id":"https://openalex.org/keywords/template-matching","display_name":"Template matching","score":0.6166644096374512},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6139978170394897},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6057165861129761},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5944222807884216},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5470898151397705},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.539550244808197},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4947459399700165},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.46628379821777344},{"id":"https://openalex.org/keywords/receiver-operating-characteristic","display_name":"Receiver operating characteristic","score":0.46337002515792847},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4006703495979309},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2722994089126587},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.20543146133422852},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1673566997051239},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.16278940439224243},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09293386340141296}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8763937950134277},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7445746660232544},{"id":"https://openalex.org/C158096908","wikidata":"https://www.wikidata.org/wiki/Q3983303","display_name":"Template matching","level":3,"score":0.6166644096374512},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6139978170394897},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6057165861129761},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5944222807884216},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5470898151397705},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.539550244808197},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4947459399700165},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.46628379821777344},{"id":"https://openalex.org/C58471807","wikidata":"https://www.wikidata.org/wiki/Q327120","display_name":"Receiver operating characteristic","level":2,"score":0.46337002515792847},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4006703495979309},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2722994089126587},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.20543146133422852},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1673566997051239},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16278940439224243},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09293386340141296},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2007-328","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.tind.io:146039","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146039","pdf_url":"http://publications.idiap.ch/downloads/reports/2007/grangier_eurospeech07.pdf","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/146039","raw_type":"Text"},{"id":"pmh:oai:infoscience.tind.io:146040","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146040","pdf_url":"https://infoscience.epfl.ch/record/146040/files/grangier_rr_07-15.pdf","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"report"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.360.2101","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.360.2101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.idiap.ch/ftp/reports/2007/grangier_eurospeech07.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:infoscience.tind.io:146039","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146039","pdf_url":"http://publications.idiap.ch/downloads/reports/2007/grangier_eurospeech07.pdf","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/146039","raw_type":"Text"},"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1567711539.pdf","grobid_xml":"https://content.openalex.org/works/W1567711539.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W56667085","https://openalex.org/W102832445","https://openalex.org/W110483337","https://openalex.org/W1491022041","https://openalex.org/W1578200545","https://openalex.org/W2088615611","https://openalex.org/W2110678746","https://openalex.org/W2112676096","https://openalex.org/W2120176508","https://openalex.org/W2120448516","https://openalex.org/W2128833328","https://openalex.org/W2151244813","https://openalex.org/W2151534206","https://openalex.org/W2155368638","https://openalex.org/W2157364932","https://openalex.org/W2159377400","https://openalex.org/W2165357419","https://openalex.org/W2167356925","https://openalex.org/W2174140043","https://openalex.org/W2914484425","https://openalex.org/W4246369350"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W1482209366","https://openalex.org/W2053269318","https://openalex.org/W2110523656","https://openalex.org/W2364370872"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,12,23,43,68],"discriminative":[4],"approach":[5,86],"to":[6,14,19,41,79,93],"template-based":[7],"keyword":[8,61],"detection.":[9],"We":[10],"introduce":[11],"method":[13],"learn":[15],"the":[16,34,39,46,49,55,60,84,96],"distance":[17,35],"used":[18],"compare":[20],"acoustic":[21],"frames,":[22],"crucial":[24],"element":[25],"for":[26,59,95],"template":[27],"matching":[28],"approaches.":[29],"The":[30,64],"proposed":[31,85],"algorithm":[32],"estimates":[33],"from":[36],"data,":[37],"with":[38],"objective":[40],"produce":[42],"detector":[44],"maximizing":[45],"Area":[47],"Under":[48],"receiver":[50],"operating":[51],"Curve":[52],"(AUC),":[53],"i.e.":[54],"standard":[56],"evaluation":[57],"measure":[58],"detection":[62],"problem.":[63],"experiments":[65],"performed":[66],"over":[67],"large":[69],"corpus,":[70],"SpeechDatII,":[71],"suggest":[72],"that":[73],"our":[74],"model":[75],"is":[76],"effective":[77],"compared":[78,92],"an":[80],"HMM":[81],"system,":[82],"e.g.":[83],"reaches":[87],"93.8\\\\%":[88],"of":[89],"averaged":[90],"AUC":[91],"87.9\\\\%":[94],"HMM.":[97]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}