{"id":"https://openalex.org/W2022366989","doi":"https://doi.org/10.1145/1774088.1774407","title":"Visual processing-inspired fern-audio features for noise-robust speaker verification","display_name":"Visual processing-inspired fern-audio features for noise-robust speaker verification","publication_year":2010,"publication_date":"2010-03-22","ids":{"openalex":"https://openalex.org/W2022366989","doi":"https://doi.org/10.1145/1774088.1774407","mag":"2022366989"},"language":"en","primary_location":{"id":"doi:10.1145/1774088.1774407","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1774088.1774407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM Symposium on Applied Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/146278","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102004126","display_name":"Anindya Roy","orcid":"https://orcid.org/0000-0002-0583-2661"},"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":true,"raw_author_name":"Anindya Roy","raw_affiliation_strings":["Idiap Research Institute, Martigny, Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Switzerland","institution_ids":["https://openalex.org/I7495430","https://openalex.org/I5124864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016330764","display_name":"S\u00e9bastien Marcel","orcid":"https://orcid.org/0000-0002-2497-9140"},"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":"S\u00e9bastien Marcel","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102004126"],"corresponding_institution_ids":["https://openalex.org/I5124864","https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":0.3382,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.56128541,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1491","last_page":"1495"},"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":0.9987000226974487,"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":0.9962999820709229,"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/computer-science","display_name":"Computer science","score":0.7948535680770874},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6078827381134033},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6077438592910767},{"id":"https://openalex.org/keywords/additive-white-gaussian-noise","display_name":"Additive white Gaussian noise","score":0.5944802165031433},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5270681381225586},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5249617099761963},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5106256604194641},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5033895373344421},{"id":"https://openalex.org/keywords/white-noise","display_name":"White noise","score":0.4775427281856537},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.45621222257614136},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4546911120414734},{"id":"https://openalex.org/keywords/gaussian-noise","display_name":"Gaussian noise","score":0.45293620228767395},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4390066862106323},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.42757388949394226},{"id":"https://openalex.org/keywords/colors-of-noise","display_name":"Colors of noise","score":0.42492786049842834},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41555604338645935},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33870893716812134},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.24893143773078918},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.14926573634147644},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11470744013786316}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7948535680770874},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6078827381134033},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6077438592910767},{"id":"https://openalex.org/C169334058","wikidata":"https://www.wikidata.org/wiki/Q353292","display_name":"Additive white Gaussian noise","level":3,"score":0.5944802165031433},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5270681381225586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5249617099761963},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5106256604194641},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5033895373344421},{"id":"https://openalex.org/C112633086","wikidata":"https://www.wikidata.org/wiki/Q381287","display_name":"White noise","level":2,"score":0.4775427281856537},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.45621222257614136},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4546911120414734},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.45293620228767395},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4390066862106323},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.42757388949394226},{"id":"https://openalex.org/C114996537","wikidata":"https://www.wikidata.org/wiki/Q4854529","display_name":"Colors of noise","level":3,"score":0.42492786049842834},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41555604338645935},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33870893716812134},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.24893143773078918},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.14926573634147644},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11470744013786316},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1774088.1774407","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1774088.1774407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM Symposium on Applied Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:146278","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146278","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.epfl.ch:146482","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146482","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:146278","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146278","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":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/G1441312571","display_name":null,"funder_award_id":"00020","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G3536194367","display_name":null,"funder_award_id":"200020-12206251NF40-111401","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G4692142516","display_name":null,"funder_award_id":"51NF40-","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G4836148144","display_name":null,"funder_award_id":"20002","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G5211510479","display_name":null,"funder_award_id":"IST-214324","funder_id":"https://openalex.org/F4320334960","funder_display_name":"Seventh Framework Programme"},{"id":"https://openalex.org/G5540487702","display_name":"Interactive Multimodal Information Management (IM)2","funder_award_id":"111401","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"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/G628552264","display_name":null,"funder_award_id":"200020","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G906399042","display_name":"MULTI: Multimodal Interaction and Multimedia Data Mining","funder_award_id":"122062","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F4320334960","display_name":"Seventh Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W83334756","https://openalex.org/W1482977908","https://openalex.org/W1527240141","https://openalex.org/W1608397235","https://openalex.org/W1667165204","https://openalex.org/W1825459403","https://openalex.org/W1830938247","https://openalex.org/W2039051707","https://openalex.org/W2097627987","https://openalex.org/W2101886560","https://openalex.org/W2121178298","https://openalex.org/W2121750345","https://openalex.org/W2129244720","https://openalex.org/W2148154194","https://openalex.org/W2618666040","https://openalex.org/W2942228371","https://openalex.org/W4233309883","https://openalex.org/W6603388714","https://openalex.org/W6631618440","https://openalex.org/W6679777549","https://openalex.org/W7024001005"],"related_works":["https://openalex.org/W1968911901","https://openalex.org/W1700578922","https://openalex.org/W2900749592","https://openalex.org/W1978190414","https://openalex.org/W2156824184","https://openalex.org/W1986743941","https://openalex.org/W2170781407","https://openalex.org/W2391895121","https://openalex.org/W2539972192","https://openalex.org/W1883569037"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,35,52,73],"consider":[4,53],"the":[5,20,30,37,44,103,106,110],"problem":[6,15,39],"of":[7,40,46,78,105,112,118],"speaker":[8,41,87],"verification":[9,42],"as":[10,54],"a":[11,75,92,97],"two-class":[12],"object":[13,21,58,71],"detection":[14,59],"in":[16,43,69,109],"computer":[17],"vision,":[18],"where":[19],"instances":[22],"are":[23],"1-D":[24],"short-time":[25],"spectral":[26],"vectors":[27],"obtained":[28],"from":[29],"speech":[31],"signal.":[32],"More":[33],"precisely,":[34],"investigate":[36],"general":[38],"presence":[45,111],"additive":[47,119],"white":[48],"Gaussian":[49],"noise,":[50],"which":[51],"analogous":[55],"to":[56,96,114],"visual":[57],"under":[60],"varying":[61],"illumination":[62],"conditions.":[63],"Inspired":[64],"by":[65],"their":[66],"recent":[67],"success":[68],"illumination-robust":[70],"detection,":[72],"apply":[74],"certain":[76],"class":[77],"binary-valued":[79],"pixel-pair":[80],"based":[81],"features":[82,108],"called":[83],"Ferns":[84],"for":[85],"noise-robust":[86],"verification.":[88],"Intensive":[89],"experiments":[90],"on":[91],"benchmark":[93],"database":[94],"according":[95],"standard":[98],"evaluation":[99],"protocol":[100],"have":[101],"shown":[102],"advantage":[104],"proposed":[107],"moderate":[113],"extremely":[115],"high":[116],"amounts":[117],"noise.":[120]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}