{"id":"https://openalex.org/W4378976870","doi":"https://doi.org/10.1109/icai58407.2023.10136626","title":"Speaker Recognition in Realistic Scenario Using Multimodal Data","display_name":"Speaker Recognition in Realistic Scenario Using Multimodal Data","publication_year":2023,"publication_date":"2023-02-22","ids":{"openalex":"https://openalex.org/W4378976870","doi":"https://doi.org/10.1109/icai58407.2023.10136626"},"language":"en","primary_location":{"id":"doi:10.1109/icai58407.2023.10136626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icai58407.2023.10136626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 3rd International Conference on Artificial Intelligence (ICAI)","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/A5049889948","display_name":"Saqlain Hussain Shah","orcid":null},"institutions":[{"id":"https://openalex.org/I173207729","display_name":"University of Engineering and Technology Taxila","ror":"https://ror.org/03v00ka07","country_code":"PK","type":"education","lineage":["https://openalex.org/I173207729"]}],"countries":["PK"],"is_corresponding":true,"raw_author_name":"Saqlain Hussain Shah","raw_affiliation_strings":["University of Engineering and Technology Taxila"],"affiliations":[{"raw_affiliation_string":"University of Engineering and Technology Taxila","institution_ids":["https://openalex.org/I173207729"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101076782","display_name":"Muhammad Saad Saeed","orcid":"https://orcid.org/0000-0002-0893-9499"},"institutions":[{"id":"https://openalex.org/I1298884728","display_name":"National Court Reporters Association","ror":"https://ror.org/00tb8hf64","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298884728"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Muhammad Saad Saeed","raw_affiliation_strings":["Swarm Robotics Lab NCRA"],"affiliations":[{"raw_affiliation_string":"Swarm Robotics Lab NCRA","institution_ids":["https://openalex.org/I1298884728"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016485532","display_name":"Shah Nawaz","orcid":"https://orcid.org/0000-0002-7715-4409"},"institutions":[{"id":"https://openalex.org/I2801876189","display_name":"Deutsches Elektronen-Synchrotron DESY","ror":"https://ror.org/01js2sh04","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2801876189"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Shah Nawaz","raw_affiliation_strings":["Deutsches Elektronen-Synchrotron DESY"],"affiliations":[{"raw_affiliation_string":"Deutsches Elektronen-Synchrotron DESY","institution_ids":["https://openalex.org/I2801876189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059502259","display_name":"Muhammad Haroon Yousaf","orcid":"https://orcid.org/0000-0001-8255-1145"},"institutions":[{"id":"https://openalex.org/I173207729","display_name":"University of Engineering and Technology Taxila","ror":"https://ror.org/03v00ka07","country_code":"PK","type":"education","lineage":["https://openalex.org/I173207729"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muhammad Haroon Yousaf","raw_affiliation_strings":["University of Engineering and Technology Taxila"],"affiliations":[{"raw_affiliation_string":"University of Engineering and Technology Taxila","institution_ids":["https://openalex.org/I173207729"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5049889948"],"corresponding_institution_ids":["https://openalex.org/I173207729"],"apc_list":null,"apc_paid":null,"fwci":2.4501,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.89790297,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"209","last_page":"213"},"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":0.9991999864578247,"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":0.9983000159263611,"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":0.8590524196624756},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.699954092502594},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.66279137134552},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6504130363464355},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6282241344451904},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.571821928024292},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.48560991883277893},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.48062294721603394},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4714706242084503},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44829487800598145},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3896733224391937},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3609640598297119},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.11625421047210693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8590524196624756},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.699954092502594},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.66279137134552},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6504130363464355},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6282241344451904},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.571821928024292},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.48560991883277893},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.48062294721603394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4714706242084503},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44829487800598145},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3896733224391937},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3609640598297119},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.11625421047210693},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icai58407.2023.10136626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icai58407.2023.10136626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 3rd International Conference on Artificial Intelligence (ICAI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W183860","https://openalex.org/W204053250","https://openalex.org/W1686810756","https://openalex.org/W2059857061","https://openalex.org/W2066078528","https://openalex.org/W2087992518","https://openalex.org/W2152305730","https://openalex.org/W2184188583","https://openalex.org/W2194775991","https://openalex.org/W2325939864","https://openalex.org/W2726515241","https://openalex.org/W2803187616","https://openalex.org/W2808631503","https://openalex.org/W2886300652","https://openalex.org/W2887997593","https://openalex.org/W2889385246","https://openalex.org/W2951237705","https://openalex.org/W2962918445","https://openalex.org/W2963173190","https://openalex.org/W2963775347","https://openalex.org/W2963801643","https://openalex.org/W2963887950","https://openalex.org/W2964171275","https://openalex.org/W2997819898","https://openalex.org/W3184648662","https://openalex.org/W4224924564","https://openalex.org/W4292947721","https://openalex.org/W4293665662","https://openalex.org/W6608353291","https://openalex.org/W6637373629","https://openalex.org/W6686207219","https://openalex.org/W6729831399","https://openalex.org/W6751420435","https://openalex.org/W6751966083","https://openalex.org/W6752791795","https://openalex.org/W6754988648","https://openalex.org/W6841945971"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2393726419"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"an":[3,128],"association":[4],"is":[5,27,46,127],"established":[6],"between":[7,130],"faces":[8,72],"and":[9,73,132],"voices":[10,74],"of":[11,22,43,71,112,118],"celebrities":[12],"leveraging":[13],"large":[14,23,49,101],"scale":[15,24,50,102],"audio-visual":[16,25,51,103],"information":[17,52,114],"from":[18,83],"YouTube.":[19],"The":[20],"availability":[21],"datasets":[26],"instrumental":[28],"in":[29,75],"developing":[30],"speaker":[31,55,92,119],"recognition":[32,56],"methods":[33],"based":[34],"on":[35,99],"standard":[36],"Convolutional":[37],"Neural":[38],"Networks.":[39],"Thus,":[40],"the":[41,84,116],"aim":[42],"this":[44,60],"paper":[45],"to":[47,53,67,87],"leverage":[48],"improve":[54],"task.":[57],"To":[58],"achieve":[59],"task,":[61],"we":[62],"proposed":[63,97],"a":[64,76,89,100],"two-branch":[65,85],"network":[66,86],"learn":[68],"joint":[69],"representations":[70],"multimodal":[77],"system.":[78],"Afterwards,":[79],"features":[80],"are":[81],"extracted":[82],"train":[88],"classifier":[90],"for":[91],"recognition.":[93,120],"We":[94],"evaluated":[95],"our":[96,122],"framework":[98],"dataset":[104],"named":[105],"VoxCelebl.":[106],"Our":[107],"results":[108,123],"show":[109],"that":[110,125],"addition":[111],"facial":[113],"improved":[115],"performance":[117],"Moreover,":[121],"indicate":[124],"there":[126],"overlap":[129],"face":[131],"voice.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
