{"id":"https://openalex.org/W2787631715","doi":"https://doi.org/10.1109/asru.2017.8268915","title":"Tackling unseen acoustic conditions in query-by-example search using time and frequency convolution for multilingual deep bottleneck features","display_name":"Tackling unseen acoustic conditions in query-by-example search using time and frequency convolution for multilingual deep bottleneck features","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2787631715","doi":"https://doi.org/10.1109/asru.2017.8268915","mag":"2787631715"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2017.8268915","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268915","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Menlo Park, CA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","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":false,"raw_author_name":"Vikramjit Mitra","raw_affiliation_strings":["SRI International, Menlo Park, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Menlo Park, CA","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":["SRI International, Menlo Park, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Menlo Park, CA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031137004","display_name":"Chris Bartels","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":"Chris Bartels","raw_affiliation_strings":["SRI International, Menlo Park, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Menlo Park, CA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"last","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":["SRI International, Menlo Park, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Menlo Park, CA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3495,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.56008498,"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":"48","last_page":"54"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9994000196456909,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/bottleneck","display_name":"Bottleneck","score":0.8464106321334839},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.7742331624031067},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7260528206825256},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.44536957144737244},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4102594256401062},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3331425189971924},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.15002188086509705},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.0697784423828125}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8464106321334839},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.7742331624031067},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7260528206825256},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.44536957144737244},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4102594256401062},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3331425189971924},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.15002188086509705},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0697784423828125},{"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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2017.8268915","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268915","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W82501063","https://openalex.org/W170732776","https://openalex.org/W1500377588","https://openalex.org/W1970890968","https://openalex.org/W1974745151","https://openalex.org/W2072349636","https://openalex.org/W2112739286","https://openalex.org/W2155273149","https://openalex.org/W2292414329","https://openalex.org/W2293535060","https://openalex.org/W2397940721","https://openalex.org/W2401449658","https://openalex.org/W2401805659","https://openalex.org/W2402401665","https://openalex.org/W2406171445","https://openalex.org/W2586232309","https://openalex.org/W2916450621","https://openalex.org/W6712625807","https://openalex.org/W6713061419","https://openalex.org/W6713188258","https://openalex.org/W6713360458"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W1001352512","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W2748922771","https://openalex.org/W1987128138","https://openalex.org/W2743976221"],"abstract_inverted_index":{"Standard":[0],"keyword":[1],"spotting":[2],"based":[3],"on":[4,12,153],"Automatic":[5],"Speech":[6],"Recognition":[7],"(ASR)":[8],"cannot":[9],"be":[10],"used":[11],"low-and":[13],"no-resource":[14],"languages":[15],"due":[16],"to":[17,36,78,124,139,142],"lack":[18,58],"of":[19,59,136,166],"annotated":[20],"data":[21,123,141],"and/or":[22],"linguistic":[23],"resources.":[24],"In":[25,104],"recent":[26],"years,":[27],"query-by-example":[28],"(QbE)":[29],"has":[30],"emerged":[31],"as":[32],"an":[33,154],"alternate":[34],"way":[35],"enroll":[37],"and":[38,48,72,75,129,132,163],"find":[39],"spoken":[40],"queries":[41],"in":[42,88,145,168],"large":[43],"audio":[44],"corpora,":[45],"yet":[46],"mismatched":[47],"unseen":[49],"acoustic":[50,147],"conditions":[51],"remain":[52],"a":[53,80],"difficult":[54],"challenge":[55],"given":[56],"the":[57,93,119,140,169],"enrollment":[60],"data.":[61],"This":[62],"paper":[63],"revisits":[64],"two":[65],"neural":[66],"network":[67],"architectures":[68],"developed":[69],"for":[70],"noise":[71,138],"channel-robust":[73],"ASR,":[74],"applies":[76],"them":[77],"building":[79],"state-of-art":[81],"multilingual":[82],"QbE":[83,115,158],"system.":[84],"By":[85],"applying":[86],"convolution":[87],"time":[89,108],"or":[90],"frequency":[91],"across":[92],"spectrum,":[94],"those":[95],"convolutional":[96],"bottlenecks":[97],"learn":[98],"more":[99,161],"discriminative":[100],"deep":[101],"bottleneck":[102],"features.":[103],"conjunction":[105],"with":[106,160],"dynamic":[107],"warping":[109],"(DTW),":[110],"these":[111],"features":[112],"enable":[113],"robust":[114],"systems.":[116],"We":[117,149],"use":[118],"MediaEval":[120],"2014":[121],"QUESST":[122],"evaluate":[125,143],"robustness":[126],"against":[127],"language":[128],"channel":[130],"mismatches,":[131],"add":[133],"several":[134],"levels":[135,165],"artificial":[137],"performance":[144,152],"degraded":[146],"environments.":[148],"also":[150],"assess":[151],"Air":[155],"Traffic":[156],"Control":[157],"task":[159],"realistic":[162],"higher":[164],"distortion":[167],"push-to-talk":[170],"domain.":[171]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}