{"id":"https://openalex.org/W2904230401","doi":"https://doi.org/10.1109/icce-berlin.2018.8576237","title":"Discriminative Deep Audio Feature Embedding for Speaker Recognition in the Wild","display_name":"Discriminative Deep Audio Feature Embedding for Speaker Recognition in the Wild","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2904230401","doi":"https://doi.org/10.1109/icce-berlin.2018.8576237","mag":"2904230401"},"language":"en","primary_location":{"id":"doi:10.1109/icce-berlin.2018.8576237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce-berlin.2018.8576237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 8th International Conference on Consumer Electronics - Berlin (ICCE-Berlin)","raw_type":"proceedings-article"},"type":"article","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/A5013570285","display_name":"Simone Bianco","orcid":"https://orcid.org/0000-0002-7070-1545"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Simone Bianco","raw_affiliation_strings":["Department of Informatics, University of Milano-Bicocca viale Sarca, 336, Milano, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Milano-Bicocca viale Sarca, 336, Milano, Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044918876","display_name":"Elia Cereda","orcid":"https://orcid.org/0000-0001-8888-3538"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Elia Cereda","raw_affiliation_strings":["Department of Informatics, University of Milano-Bicocca viale Sarca, 336, Milano, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Milano-Bicocca viale Sarca, 336, Milano, Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053344554","display_name":"Paolo Napoletano","orcid":"https://orcid.org/0000-0001-9112-0574"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Napoletano","raw_affiliation_strings":["Department of Informatics, University of Milano-Bicocca viale Sarca, 336, Milano, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Milano-Bicocca viale Sarca, 336, Milano, Italy","institution_ids":["https://openalex.org/I66752286"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5013570285"],"corresponding_institution_ids":["https://openalex.org/I66752286"],"apc_list":null,"apc_paid":null,"fwci":0.4887,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74018837,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"14","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.828471302986145},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8162184953689575},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7454483509063721},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7112846374511719},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6937315464019775},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6294663548469543},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.605576753616333},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6043795347213745},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5792607069015503},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5583427548408508},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5563190579414368},{"id":"https://openalex.org/keywords/residual-neural-network","display_name":"Residual neural network","score":0.5118696093559265},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.47059571743011475},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.45298653841018677},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4379864037036896},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.0882171094417572}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.828471302986145},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8162184953689575},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7454483509063721},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7112846374511719},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6937315464019775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6294663548469543},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.605576753616333},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6043795347213745},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5792607069015503},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5583427548408508},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5563190579414368},{"id":"https://openalex.org/C2944601119","wikidata":"https://www.wikidata.org/wiki/Q43744058","display_name":"Residual neural network","level":3,"score":0.5118696093559265},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.47059571743011475},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.45298653841018677},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4379864037036896},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0882171094417572},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icce-berlin.2018.8576237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce-berlin.2018.8576237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 8th International Conference on Consumer Electronics - Berlin (ICCE-Berlin)","raw_type":"proceedings-article"},{"id":"pmh:oai:boa.unimib.it:10281/215439","is_oa":false,"landing_page_url":"http://hdl.handle.net/10281/215439","pdf_url":null,"source":{"id":"https://openalex.org/S4306401259","display_name":"BOA (University of Milano-Bicocca)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66752286","host_organization_name":"University of Milano-Bicocca","host_organization_lineage":["https://openalex.org/I66752286"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7300000190734863}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W204053250","https://openalex.org/W2041823554","https://openalex.org/W2096733369","https://openalex.org/W2129244720","https://openalex.org/W2144172034","https://openalex.org/W2150769028","https://openalex.org/W2165880886","https://openalex.org/W2194775991","https://openalex.org/W2286133382","https://openalex.org/W2398826216","https://openalex.org/W2470254032","https://openalex.org/W2520774990","https://openalex.org/W2526050071","https://openalex.org/W2549349626","https://openalex.org/W2612434969","https://openalex.org/W2726515241","https://openalex.org/W2963173190","https://openalex.org/W2963430102","https://openalex.org/W3099206234","https://openalex.org/W4248480789","https://openalex.org/W6608353291","https://openalex.org/W6648737282","https://openalex.org/W6681239517","https://openalex.org/W6712560600","https://openalex.org/W6737575990"],"related_works":["https://openalex.org/W4384929466","https://openalex.org/W2206035908","https://openalex.org/W3148366653","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"face":[4],"the":[5,11,15,22,32,46,49,67,74,84,87,93,96],"problem":[6],"of":[7,24,34,48,86,95],"speaker":[8,16,75],"recognition":[9],"in":[10,40,105,117],"wild.":[12],"We":[13,30],"tackle":[14],"identification":[17,76],"and":[18,69,77],"verification":[19,78],"problems":[20],"with":[21,45,59,90],"use":[23],"Deep":[25],"Convolutional":[26],"Neural":[27],"Networks":[28],"(CNN).":[29],"propose":[31],"modification":[33],"two":[35],"Residual":[36],"CNN":[37],"architectures":[38],"(ResNet)":[39],"order":[41],"to":[42,92,102,113],"be":[43,103,114],"used":[44],"spectrograms":[47],"audio":[50],"data":[51],"as":[52],"input":[53],"images.":[54],"The":[55,80,98],"proposed":[56,88,99],"architectures,":[57],"trained":[58],"a":[60,118],"contrastive-center":[61],"loss,":[62],"have":[63],"been":[64],"tested":[65],"on":[66,72],"VoxCeleb":[68],"SIWIS":[70],"datasets":[71],"both":[73],"tasks.":[79],"experimental":[81],"results":[82],"show":[83],"effectiveness":[85],"solution":[89],"respect":[91],"state":[94],"art.":[97],"network":[100],"shows":[101,112],"robust":[104,116],"unconstrained":[106],"conditions":[107],"and,":[108],"more":[109],"important,":[110],"it":[111],"quite":[115],"multilingual":[119],"scenario.":[120]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}