{"id":"https://openalex.org/W6903423159","doi":"https://doi.org/10.1109/tencon61640.2024.10903050","title":"Speaker Recognition Using Deep Learning Techniques","display_name":"Speaker Recognition Using Deep Learning Techniques","publication_year":2024,"publication_date":"2024-12-01","ids":{"openalex":"https://openalex.org/W6903423159","doi":"https://doi.org/10.1109/tencon61640.2024.10903050"},"language":"en","primary_location":{"id":"doi:10.1109/tencon61640.2024.10903050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tencon61640.2024.10903050","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TENCON 2024 - 2024 IEEE Region 10 Conference (TENCON)","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":null,"display_name":"Maninder Maan","orcid":null},"institutions":[{"id":"https://openalex.org/I162030827","display_name":"Thapar Institute of Engineering & Technology","ror":"https://ror.org/00wdq3744","country_code":"IN","type":"education","lineage":["https://openalex.org/I162030827"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Maninder Maan","raw_affiliation_strings":["Thapar University,Dept of CSED,Patiala,Punjab,India"],"affiliations":[{"raw_affiliation_string":"Thapar University,Dept of CSED,Patiala,Punjab,India","institution_ids":["https://openalex.org/I162030827"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kabir Kapur","orcid":null},"institutions":[{"id":"https://openalex.org/I162030827","display_name":"Thapar Institute of Engineering & Technology","ror":"https://ror.org/00wdq3744","country_code":"IN","type":"education","lineage":["https://openalex.org/I162030827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kabir Kapur","raw_affiliation_strings":["Thapar University,Dept of EIED,Patiala,Punjab,India"],"affiliations":[{"raw_affiliation_string":"Thapar University,Dept of EIED,Patiala,Punjab,India","institution_ids":["https://openalex.org/I162030827"]}]},{"author_position":"last","author":{"id":null,"display_name":"Arun Singh Pundir","orcid":null},"institutions":[{"id":"https://openalex.org/I162030827","display_name":"Thapar Institute of Engineering & Technology","ror":"https://ror.org/00wdq3744","country_code":"IN","type":"education","lineage":["https://openalex.org/I162030827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Arun Singh Pundir","raw_affiliation_strings":["Thapar University,Dept of CSED,Patiala,Punjab,India"],"affiliations":[{"raw_affiliation_string":"Thapar University,Dept of CSED,Patiala,Punjab,India","institution_ids":["https://openalex.org/I162030827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162030827"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32795024,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1155","last_page":"1158"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.3440999984741211,"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":0.3440999984741211,"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/T10863","display_name":"Voice and Speech Disorders","score":0.3192000091075897,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.051100000739097595,"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/categorization","display_name":"Categorization","score":0.6797999739646912},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6355999708175659},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.567799985408783},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5192999839782715},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.47110000252723694},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.44200000166893005},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.3984000086784363},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3937000036239624}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7675999999046326},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6797999739646912},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6398000121116638},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6355999708175659},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.567799985408783},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5386000275611877},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5192999839782715},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.47110000252723694},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.44200000166893005},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3937000036239624},{"id":"https://openalex.org/C141668000","wikidata":"https://www.wikidata.org/wiki/Q10991973","display_name":"Hotline","level":2,"score":0.3668999969959259},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3181999921798706},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.29510000348091125},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.2865000069141388},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C2777858628","wikidata":"https://www.wikidata.org/wiki/Q1111837","display_name":"Interactive voice response","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2745000123977661},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tencon61640.2024.10903050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tencon61640.2024.10903050","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TENCON 2024 - 2024 IEEE Region 10 Conference (TENCON)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.45095980167388916},{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4504460394382477}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W88923019","https://openalex.org/W1565144712","https://openalex.org/W2059322891","https://openalex.org/W2618530766","https://openalex.org/W6633808362","https://openalex.org/W6637404493","https://openalex.org/W6678856934","https://openalex.org/W6683113847","https://openalex.org/W6701891365","https://openalex.org/W6910681941"],"related_works":[],"abstract_inverted_index":{"Accurately":[0],"classifying":[1],"age":[2,69,130],"and":[3,11,28,48,63,93,110,131],"gender":[4,53,132],"using":[5,111,120],"sound":[6],"is":[7,21,38,55],"beneficial":[8],"for":[9,26,116],"speaker":[10],"speech":[12,17],"recognition":[13],"as":[14,16,45],"well":[15],"emotion":[18],"classification.":[19],"This":[20,87],"because":[22],"separate":[23],"acoustic":[24],"models":[25],"men":[27],"women":[29],"have":[30,135],"been":[31],"shown":[32],"to":[33,75,77,100],"perform":[34],"better.":[35],"Gender-based":[36],"labelling":[37],"widely":[39],"used":[40,144],"in":[41,57,60,65,96],"image-related":[42],"applications":[43],"such":[44],"video":[46],"summary":[47],"robot-human":[49],"interaction.":[50],"Even":[51],"still,":[52],"classification":[54,70,117],"still":[56],"its":[58],"infancy":[59],"voice":[61,157],"processing":[62],"advanced":[64],"image":[66],"processing.":[67],"Accurate":[68],"helps":[71],"determine":[72],"how":[73],"best":[74],"respond":[76],"a":[78,84,137],"given":[79],"user":[80],"who":[81],"fits":[82],"into":[83,127],"certain":[85],"group.":[86],"can":[88],"assist":[89],"customer":[90],"service":[91],"organizations":[92],"emergency":[94],"hotlines":[95],"tailoring":[97],"their":[98,104],"answer":[99],"the":[101,128,150,155],"individual":[102],"requiring":[103],"help.":[105],"After":[106],"meticulous":[107],"manual":[108],"selection":[109],"established":[112],"methods,":[113],"characteristics":[114,153],"retrieved":[115],"are":[118],"chosen":[119],"machine":[121],"learning":[122],"models.":[123],"To":[124],"categorize":[125],"data":[126],"appropriate":[129],"classes,":[133],"we":[134,143],"employed":[136],"variety":[138],"of":[139,154],"straightforward":[140],"classifiers.":[141],"Additionally,":[142],"various":[145],"convolutional":[146],"neural":[147],"networks":[148],"with":[149],"power":[151],"spectrum":[152],"acquired":[156],"samples.":[158]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}