{"id":"https://openalex.org/W3097741049","doi":"https://doi.org/10.21437/interspeech.2020-1814","title":"Audio-Visual Speaker Recognition with a Cross-Modal Discriminative Network","display_name":"Audio-Visual Speaker Recognition with a Cross-Modal Discriminative Network","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3097741049","doi":"https://doi.org/10.21437/interspeech.2020-1814","mag":"3097741049"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1814","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1814","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5026034735","display_name":"Ruijie Tao","orcid":"https://orcid.org/0000-0003-0021-5661"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ruijie Tao","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029637694","display_name":"Rohan Kumar Das","orcid":"https://orcid.org/0000-0002-1332-3357"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Rohan Kumar Das","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I180437899","display_name":"University of Bremen","ror":"https://ror.org/04ers2y35","country_code":"DE","type":"education","lineage":["https://openalex.org/I180437899"]}],"countries":["DE","SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore","Machine Listening Lab, University of Bremen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Machine Listening Lab, University of Bremen, Germany","institution_ids":["https://openalex.org/I180437899"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.4223,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.95991561,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2242","last_page":"2246"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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":0.9980999827384949,"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/discriminative-model","display_name":"Discriminative model","score":0.8201948404312134},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7646316885948181},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6956022381782532},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6731201410293579},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5028395056724548},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49151310324668884},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4613265097141266},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34514063596725464},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.08569714426994324}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8201948404312134},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7646316885948181},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6956022381782532},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6731201410293579},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5028395056724548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49151310324668884},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4613265097141266},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34514063596725464},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.08569714426994324},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1814","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1814","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1971887133","https://openalex.org/W2076462394","https://openalex.org/W2127013860","https://openalex.org/W2170088868","https://openalex.org/W2227324914","https://openalex.org/W2295590090","https://openalex.org/W2490959726","https://openalex.org/W2515770085","https://openalex.org/W2619383789","https://openalex.org/W2621109248","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2897663715","https://openalex.org/W2938358845","https://openalex.org/W2941320063","https://openalex.org/W2943235166","https://openalex.org/W2951237705","https://openalex.org/W2962918445","https://openalex.org/W2963566548","https://openalex.org/W2963801643","https://openalex.org/W2963887950","https://openalex.org/W2969985801","https://openalex.org/W2972961496","https://openalex.org/W2979157532","https://openalex.org/W2982474723","https://openalex.org/W2991096973","https://openalex.org/W2997819898","https://openalex.org/W3022697898","https://openalex.org/W3026006730","https://openalex.org/W3101998545","https://openalex.org/W3123318516","https://openalex.org/W3131194065"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W3148366653","https://openalex.org/W4313854686","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2368768466","https://openalex.org/W2757081366"],"abstract_inverted_index":{"Audio-visual":[0],"speaker":[1,13,65],"recognition":[2,14],"is":[3],"one":[4],"of":[5,87],"the":[6,9,25,35,52,78],"tasks":[7],"in":[8,17,34],"recent":[10],"2019":[11,88],"NIST":[12,89],"evaluation":[15,85],"(SRE).Studies":[16],"neuroscience":[18],"and":[19,29,58],"computer":[20],"science":[21],"all":[22],"point":[23],"to":[24,40],"fact":[26],"that":[27,50,61],"vision":[28],"auditory":[30],"neural":[31],"signals":[32],"interact":[33],"cognitive":[36],"process.This":[37],"motivated":[38],"us":[39],"study":[41],"a":[42],"cross-modal":[43],"network,":[44],"namely":[45],"voice-face":[46],"discriminative":[47,66],"network":[48],"(VFNet)":[49],"establishes":[51],"general":[53],"relation":[54],"between":[55],"human":[56],"voice":[57],"face.Experiments":[59],"show":[60],"VFNet":[62],"provides":[63],"additional":[64],"information.With":[67],"VFNet,":[68],"we":[69],"achieve":[70],"16.54%":[71],"equal":[72],"error":[73],"rate":[74],"relative":[75],"reduction":[76],"over":[77],"score":[79],"level":[80],"fusion":[81],"audio-visual":[82],"baseline":[83],"on":[84],"set":[86],"SRE.":[90]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}
