{"id":"https://openalex.org/W4393406263","doi":"https://doi.org/10.1109/o-cocosda60357.2023.10482931","title":"Investigating Activation Functions to Enhance Speaker Identification with LSTM Networks","display_name":"Investigating Activation Functions to Enhance Speaker Identification with LSTM Networks","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4393406263","doi":"https://doi.org/10.1109/o-cocosda60357.2023.10482931"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda60357.2023.10482931","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/o-cocosda60357.2023.10482931","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 26th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","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/A5063568064","display_name":"Pooja Gambhir","orcid":"https://orcid.org/0000-0001-9299-1128"},"institutions":[{"id":"https://openalex.org/I4210143260","display_name":"Indira Gandhi Delhi Technical University for Women","ror":"https://ror.org/057c5p638","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210143260"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pooja Gambhir","raw_affiliation_strings":["Indira Gandhi Delhi Technical University for Women,Department of Information Technology,Delhi,India","Department of Information Technology, Indira Gandhi Delhi Technical University for Women, Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indira Gandhi Delhi Technical University for Women,Department of Information Technology,Delhi,India","institution_ids":["https://openalex.org/I4210143260"]},{"raw_affiliation_string":"Department of Information Technology, Indira Gandhi Delhi Technical University for Women, Delhi, India","institution_ids":["https://openalex.org/I4210143260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022991626","display_name":"Amita Dev","orcid":"https://orcid.org/0000-0002-6926-9433"},"institutions":[{"id":"https://openalex.org/I4210143260","display_name":"Indira Gandhi Delhi Technical University for Women","ror":"https://ror.org/057c5p638","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210143260"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Amita Dev","raw_affiliation_strings":["Indira Gandhi Delhi Technical University for Women,Department of Information Technology,Delhi,India","Department of Information Technology, Indira Gandhi Delhi Technical University for Women, Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indira Gandhi Delhi Technical University for Women,Department of Information Technology,Delhi,India","institution_ids":["https://openalex.org/I4210143260"]},{"raw_affiliation_string":"Department of Information Technology, Indira Gandhi Delhi Technical University for Women, Delhi, India","institution_ids":["https://openalex.org/I4210143260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102886753","display_name":"Poonam Bansal","orcid":"https://orcid.org/0000-0002-8214-2840"},"institutions":[{"id":"https://openalex.org/I4210143260","display_name":"Indira Gandhi Delhi Technical University for Women","ror":"https://ror.org/057c5p638","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210143260"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Poonam Bansal","raw_affiliation_strings":["Indira Gandhi Delhi Technical University for Women,Department of AI and Data Science,Delhi,India","Department of AI and Data Science, Indira Gandhi Delhi Technical University for Women, Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indira Gandhi Delhi Technical University for Women,Department of AI and Data Science,Delhi,India","institution_ids":["https://openalex.org/I4210143260"]},{"raw_affiliation_string":"Department of AI and Data Science, Indira Gandhi Delhi Technical University for Women, Delhi, India","institution_ids":["https://openalex.org/I4210143260"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1632,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.6048528,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"2","issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9929999709129333,"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":0.9929999709129333,"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":0.9635999798774719,"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/T10860","display_name":"Speech and Audio Processing","score":0.9549000263214111,"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":0.7340512275695801},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.7212338447570801},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.5925102233886719},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5207673907279968},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4802860915660858},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4278481602668762}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7340512275695801},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.7212338447570801},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.5925102233886719},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5207673907279968},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4802860915660858},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4278481602668762},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda60357.2023.10482931","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/o-cocosda60357.2023.10482931","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 26th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","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":35,"referenced_works":["https://openalex.org/W1563637739","https://openalex.org/W1791154168","https://openalex.org/W2007645738","https://openalex.org/W2053831280","https://openalex.org/W2103496339","https://openalex.org/W2107878631","https://openalex.org/W2108866614","https://openalex.org/W2109004813","https://openalex.org/W2154278880","https://openalex.org/W2158798595","https://openalex.org/W2259317772","https://openalex.org/W2293634267","https://openalex.org/W2326699523","https://openalex.org/W2406392101","https://openalex.org/W2560674852","https://openalex.org/W2783208898","https://openalex.org/W2798765714","https://openalex.org/W2913127908","https://openalex.org/W2919448963","https://openalex.org/W2922413936","https://openalex.org/W2960094668","https://openalex.org/W2964052309","https://openalex.org/W2972627751","https://openalex.org/W2975686734","https://openalex.org/W3015152809","https://openalex.org/W3016562044","https://openalex.org/W3022585112","https://openalex.org/W3199044515","https://openalex.org/W4200082326","https://openalex.org/W4299379403","https://openalex.org/W4365152319","https://openalex.org/W6631943919","https://openalex.org/W6637242042","https://openalex.org/W6664008549","https://openalex.org/W6767827008"],"related_works":["https://openalex.org/W2410566519","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W4234190324","https://openalex.org/W321304764","https://openalex.org/W3162054169","https://openalex.org/W2249138175","https://openalex.org/W2154141294","https://openalex.org/W3035928819"],"abstract_inverted_index":{"Speaker":[0,79],"identification":[1,120,127],"refers":[2],"to":[3,30,71,89],"the":[4,8,76,86,94,99,126],"task":[5],"of":[6,10,22,78,96,110,117,128,146],"localising":[7],"identity":[9],"a":[11,19],"person":[12],"with":[13,53,65,121,140],"their":[14],"voice.":[15,148],"This":[16,68],"undertaking":[17],"demands":[18],"comprehensive":[20],"understanding":[21],"both":[23],"visual":[24],"and":[25,35,58,92],"auditory":[26],"cues,":[27],"necessitating":[28],"resilience":[29],"manage":[31],"significant":[32],"quality":[33],"impairments":[34],"unbounded":[36],"variations":[37],"in":[38,75],"content.":[39],"The":[40,101],"paper":[41],"presents":[42],"an":[43],"innovative":[44],"approach":[45,69],"that":[46,131],"integrates":[47],"Long":[48],"Short-Term":[49],"Memory":[50],"(LSTM)":[51],"architecture":[52],"Recurrent":[54,60],"Neural":[55],"Networks":[56],"(RNN)":[57],"Gated":[59],"Unit":[61],"(GRU),":[62],"incorporating":[63],"fine-tuning":[64],"activation":[66,138],"functions.":[67],"aims":[70,114],"assess":[72],"its":[73],"effectiveness":[74],"field":[77],"Recognition.":[80],"Activation":[81],"functions":[82],"are":[83],"used":[84],"within":[85],"LSTM":[87],"cells":[88],"introduce":[90],"non-linearity":[91],"control":[93],"flow":[95],"information":[97],"through":[98],"network.":[100],"present":[102],"work":[103],"is":[104],"evaluated":[105],"using":[106],"Hindi":[107],"audio":[108],"dataset":[109],"100":[111],"speakers,":[112],"which":[113],"at":[115],"assessment":[116],"text-independent":[118],"speaker":[119,129],"noisy":[122],"background.":[123],"Results":[124],"on":[125],"show":[130],"tanh":[132],"performed":[133],"effectively":[134],"stronger":[135],"than":[136],"other":[137],"functions,":[139],"LSTM-GRU":[141],"for":[142],"capturing":[143],"intricate":[144],"characteristics":[145],"speaker\u2019s":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}