{"id":"https://openalex.org/W2887949187","doi":"https://doi.org/10.21437/interspeech.2018-1240","title":"On Learning to Identify Genders from Raw Speech Signal Using CNNs","display_name":"On Learning to Identify Genders from Raw Speech Signal Using CNNs","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2887949187","doi":"https://doi.org/10.21437/interspeech.2018-1240","mag":"2887949187"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1240","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/256287","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064475436","display_name":"Selen Hande Kabil","orcid":"https://orcid.org/0000-0002-2588-4047"},"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"]},{"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"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Selen Hande Kabil","raw_affiliation_strings":["Idiap Research Institute, Martigny, CH","\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, CH"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, CH","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, CH","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047091215","display_name":"Hannah Muckenhirn","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":"Hannah Muckenhirn","raw_affiliation_strings":["\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, CH","Idiap Research Institute, Martigny, CH"],"affiliations":[{"raw_affiliation_string":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, CH","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, CH","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043551083","display_name":"Mathew Magimai.-Doss","orcid":"https://orcid.org/0000-0002-8714-1409"},"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":"Mathew Magimai.-Doss","raw_affiliation_strings":["Idiap Research Institute, Martigny, CH"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, CH","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5064475436"],"corresponding_institution_ids":["https://openalex.org/I5124864","https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":4.7236,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.95904514,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"287","last_page":"291"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994999766349792,"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":0.9975000023841858,"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":0.7189675569534302},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6164937615394592},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4822748005390167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44955310225486755},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.355319082736969}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7189675569534302},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6164937615394592},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4822748005390167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44955310225486755},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.355319082736969},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2018-1240","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:256287","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/256287","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":null,"raw_type":"conference proceedings"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:256287","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/256287","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":null,"raw_type":"conference proceedings"},"sustainable_development_goals":[{"display_name":"Gender equality","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W106160982","https://openalex.org/W753012316","https://openalex.org/W1608661022","https://openalex.org/W1638038541","https://openalex.org/W1996601463","https://openalex.org/W2008291900","https://openalex.org/W2057563799","https://openalex.org/W2063125572","https://openalex.org/W2070696251","https://openalex.org/W2129456397","https://openalex.org/W2168966732","https://openalex.org/W2176804518","https://openalex.org/W2291299091","https://openalex.org/W2398826216","https://openalex.org/W2399733683","https://openalex.org/W2492342376","https://openalex.org/W2513345070","https://openalex.org/W2566781703","https://openalex.org/W2738359832","https://openalex.org/W2770454110","https://openalex.org/W2886891848","https://openalex.org/W2963175699","https://openalex.org/W4233131682"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W3192589309"],"abstract_inverted_index":{"Automatic":[0],"Gender":[1],"Recognition":[2],"(AGR)":[3],"is":[4],"the":[5,9,29,42,69,147,162,166],"task":[6],"of":[7,11,44,161],"identifying":[8],"gender":[10,84,125,175],"a":[12,15,34,57,78,97,103,112],"speaker":[13,49],"given":[14],"speech":[16,30,46,71,119],"signal.":[17],"Standard":[18],"approaches":[19],"extract":[20],"features":[21,27,62,156],"like":[22],"fundamental":[23,171],"frequency":[24,172],"and":[25,32,51,63,101,123,136,170],"cepstral":[26],"from":[28,38,68],"signal":[31,72,120],"train":[33],"binary":[35],"classifier.":[36],"Inspired":[37],"recent":[39],"works":[40],"in":[41,73],"area":[43],"automatic":[45],"recognition":[47,50],"(ASR),":[48],"presentation":[52],"attack":[53],"detection,":[54],"we":[55],"present":[56],"novel":[58],"approach":[59,149],"where":[60],"relevant":[61],"classifier":[64,85],"are":[65],"jointly":[66],"learned":[67],"raw":[70,118],"end-to-end":[74],"manner.":[75],"We":[76],"propose":[77],"convolutional":[79],"neural":[80],"networks":[81],"(CNN)":[82],"based":[83,157],"that":[86,143,165],"consists":[87],"of:":[88],"(1)":[89],"convolution":[90],"layers,":[91],"which":[92,107],"can":[93,108],"be":[94,109],"interpreted":[95,110],"as":[96,111,121],"feature":[98],"learning":[99],"stage":[100],"(2)":[102],"multilayer":[104],"perceptron":[105],"(MLP),":[106],"classification":[113],"stage.":[114],"The":[115],"system":[116,152],"takes":[117],"input,":[122],"outputs":[124],"posterior":[126],"probabilities.":[127],"Experimental":[128],"studies":[129],"conducted":[130],"on":[131],"two":[132],"datasets,":[133],"namely":[134],"AVspoof":[135],"ASVspoof":[137],"2015,":[138],"with":[139,144],"different":[140],"architectures":[141,146],"show":[142,164],"simple":[145],"proposed":[148],"yields":[150],"better":[151],"than":[153],"standard":[154],"acoustic":[155],"approach.":[158],"Further":[159],"analysis":[160],"CNNs":[163,167],"learn":[168],"formant":[169],"information":[173],"for":[174],"identification.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}