{"id":"https://openalex.org/W2990013535","doi":"https://doi.org/10.1109/taslp.2020.2988788","title":"Neural Network Based End-to-End Query by Example Spoken Term Detection","display_name":"Neural Network Based End-to-End Query by Example Spoken Term Detection","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W2990013535","doi":"https://doi.org/10.1109/taslp.2020.2988788","mag":"2990013535"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.2988788","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2988788","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1911.08332","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103133511","display_name":"Dhananjay Ram","orcid":"https://orcid.org/0000-0003-1822-9199"},"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":true,"raw_author_name":"Dhananjay Ram","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland","IDIAP RESEARCH INSTITUTE"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP RESEARCH INSTITUTE","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016284564","display_name":"Lesly Miculicich","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"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":"Lesly Miculicich","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland","\u00c9cole Polytechnic F\u00e9d\u00e9rale de Lausanne (EPFL), Lausanne, Switzerland","Idiap Research Institute, , Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"\u00c9cole Polytechnic F\u00e9d\u00e9rale de Lausanne (EPFL), Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Idiap Research Institute, , Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108187466","display_name":"Herv\u00e9 Bourlard","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"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":"Herve Bourlard","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland","\u00c9cole Polytechnic F\u00e9d\u00e9rale de Lausanne (EPFL), Lausanne, Switzerland","Idiap Research Institute, , Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"\u00c9cole Polytechnic F\u00e9d\u00e9rale de Lausanne (EPFL), Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Idiap Research Institute, , Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103133511"],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00843275,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"1416","last_page":"1427"},"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":0.9988999962806702,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9965999722480774,"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/computer-science","display_name":"Computer science","score":0.8542783260345459},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.8330508470535278},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.7245784401893616},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.656362771987915},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.545127272605896},{"id":"https://openalex.org/keywords/query-by-example","display_name":"Query by Example","score":0.5283967852592468},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5225836038589478},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5222597718238831},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49645787477493286},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.46857476234436035},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43736910820007324},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.42971423268318176},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4189188480377197},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41524988412857056},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.19751426577568054},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.16987240314483643},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.08926567435264587}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8542783260345459},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8330508470535278},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.7245784401893616},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.656362771987915},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.545127272605896},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.5283967852592468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5225836038589478},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5222597718238831},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49645787477493286},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.46857476234436035},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43736910820007324},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.42971423268318176},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4189188480377197},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41524988412857056},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.19751426577568054},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.16987240314483643},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.08926567435264587},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/taslp.2020.2988788","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2988788","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1911.08332","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.08332","pdf_url":"https://arxiv.org/pdf/1911.08332","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2990013535","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1911.08332","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:infoscience.epfl.ch:278156","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/278156","pdf_url":null,"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":"WoS","raw_type":"research article"},{"id":"doi:10.48550/arxiv.1911.08332","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1911.08332","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1911.08332","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.08332","pdf_url":"https://arxiv.org/pdf/1911.08332","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5599649393","display_name":null,"funder_award_id":"200020","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5921281487","display_name":null,"funder_award_id":"number","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W54398672","https://openalex.org/W103757200","https://openalex.org/W170732776","https://openalex.org/W228764207","https://openalex.org/W1490960657","https://openalex.org/W1496120315","https://openalex.org/W1524333225","https://openalex.org/W1686810756","https://openalex.org/W1970890968","https://openalex.org/W1983042831","https://openalex.org/W2084534958","https://openalex.org/W2100768664","https://openalex.org/W2114347655","https://openalex.org/W2123237149","https://openalex.org/W2126203737","https://openalex.org/W2128160875","https://openalex.org/W2137044559","https://openalex.org/W2152354149","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2171019095","https://openalex.org/W2296362153","https://openalex.org/W2322223754","https://openalex.org/W2513125788","https://openalex.org/W2616503791","https://openalex.org/W2618530766","https://openalex.org/W2767122664","https://openalex.org/W2886144785","https://openalex.org/W2888775821","https://openalex.org/W2888951652","https://openalex.org/W2913340405","https://openalex.org/W2963879374","https://openalex.org/W2964121744","https://openalex.org/W3007486152","https://openalex.org/W3010656005","https://openalex.org/W6602170065","https://openalex.org/W6608930086","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6632583289","https://openalex.org/W6637373629","https://openalex.org/W6675022971","https://openalex.org/W6678292227","https://openalex.org/W6738286880","https://openalex.org/W6779817130","https://openalex.org/W6780226713","https://openalex.org/W6884732673"],"related_works":["https://openalex.org/W3019546258","https://openalex.org/W3118322613","https://openalex.org/W2809621655","https://openalex.org/W2573379274","https://openalex.org/W2895358653","https://openalex.org/W3009746329","https://openalex.org/W3142385198","https://openalex.org/W2371039490","https://openalex.org/W2962723475","https://openalex.org/W3127512039","https://openalex.org/W3207762685","https://openalex.org/W2945894404","https://openalex.org/W2946508582","https://openalex.org/W2922283382","https://openalex.org/W3109671931","https://openalex.org/W2904077174","https://openalex.org/W2766219058","https://openalex.org/W3082696729","https://openalex.org/W2908497602","https://openalex.org/W2746301562"],"abstract_inverted_index":{"This":[0],"article":[1],"focuses":[2],"on":[3,21,152,166],"the":[4,69,89,105],"problem":[5],"of":[6,112,119,142],"query":[7],"by":[8,163],"example":[9],"spoken":[10],"term":[11],"detection":[12],"(QbE-STD)":[13],"in":[14,129,171],"zero-resource":[15],"scenario.":[16],"State-of-the-art":[17],"approaches":[18,149],"primarily":[19],"rely":[20],"dynamic":[22],"time":[23],"warping":[24],"(DTW)":[25],"based":[26,71,79,91,95,134],"template":[27],"matching":[28,72,80,92,96,110],"techniques":[29],"using":[30,82,97],"phone":[31],"posterior":[32,83],"or":[33],"bottleneck":[34,49,98],"features":[35,55,99],"extracted":[36],"from":[37],"a":[38,77,130],"deep":[39],"neural":[40,132],"network":[41,133],"(DNN).":[42],"We":[43,122],"use":[44],"both":[45],"monolingual":[46],"and":[47,51,108,161],"multilingual":[48,54,155],"features,":[50],"show":[52,87],"that":[53,68,88],"perform":[56],"increasingly":[57],"better":[58],"with":[59,76],"more":[60],"training":[61],"languages.":[62],"Previously,":[63],"it":[64],"has":[65],"been":[66],"shown":[67],"DTW":[70,94],"can":[73],"be":[74],"replaced":[75],"CNN":[78,90],"while":[81],"features.":[84],"Here,":[85],"we":[86],"outperforms":[93],"as":[100],"well.":[101],"In":[102],"this":[103],"case,":[104],"feature":[106],"extraction":[107],"pattern":[109],"stages":[111,128,145],"our":[113],"QbE-STD":[114],"system":[115],"are":[116,150],"optimized":[117],"independently":[118],"each":[120,172],"other.":[121],"propose":[123],"to":[124,138],"integrate":[125],"these":[126],"two":[127,144,153],"fully":[131],"end-to-end":[135],"learning":[136],"framework":[137],"enable":[139],"joint":[140],"optimization":[141],"those":[143],"simultaneously.":[146],"The":[147],"proposed":[148],"evaluated":[151],"challenging":[154],"datasets:":[156],"Spoken":[157],"Web":[158],"Search":[159,165],"2013":[160],"Query":[162],"Example":[164],"Speech":[167],"Task":[168],"2014,":[169],"demonstrating":[170],"case":[173],"significant":[174],"improvements.":[175]},"counts_by_year":[],"updated_date":"2026-03-15T09:29:46.208133","created_date":"2025-10-10T00:00:00"}