{"id":"https://openalex.org/W7124856885","doi":"https://doi.org/10.1109/icaaic64647.2025.11330488","title":"Emotion-Aware Speaker Diarization Based on Prosodic and Deep Embedding Integration","display_name":"Emotion-Aware Speaker Diarization Based on Prosodic and Deep Embedding Integration","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W7124856885","doi":"https://doi.org/10.1109/icaaic64647.2025.11330488"},"language":"en","primary_location":{"id":"doi:10.1109/icaaic64647.2025.11330488","doi":"https://doi.org/10.1109/icaaic64647.2025.11330488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaaic64647.2025.11330488","pdf_url":null,"source":{"id":"https://openalex.org/S4363607845","display_name":"International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 4th International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5048148086","display_name":"Kamoliddin Shukurov","orcid":"https://orcid.org/0000-0003-2777-0817","observed_orcids":["https://orcid.org/0000-0003-2777-0817"]},"institutions":[{"id":"https://openalex.org/I21256249","display_name":"Tashkent University of Information Technology","ror":"https://ror.org/05987a729","country_code":"UZ","type":"education","lineage":["https://openalex.org/I21256249"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Kamoliddin Shukurov","raw_affiliation_strings":["TUIT named after Mukhammad al-Khwarizmi,Department of robotics and intelligent systems,Tashkent,Uzbekistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TUIT named after Mukhammad al-Khwarizmi,Department of robotics and intelligent systems,Tashkent,Uzbekistan","institution_ids":["https://openalex.org/I21256249"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078245790","display_name":"U U Khasanov","orcid":"https://orcid.org/0009-0002-1064-3758","observed_orcids":["https://orcid.org/0009-0002-1064-3758"]},"institutions":[{"id":"https://openalex.org/I21256249","display_name":"Tashkent University of Information Technology","ror":"https://ror.org/05987a729","country_code":"UZ","type":"education","lineage":["https://openalex.org/I21256249"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Umidjon Khasanov","raw_affiliation_strings":["TUIT named after Mukhammad al-Khwarizmi,Department of robotics and intelligent systems,Tashkent,Uzbekistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TUIT named after Mukhammad al-Khwarizmi,Department of robotics and intelligent systems,Tashkent,Uzbekistan","institution_ids":["https://openalex.org/I21256249"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073481187","display_name":"Shokhrukhmirzo Kholdorov","orcid":"https://orcid.org/0000-0003-2686-4627","observed_orcids":["https://orcid.org/0000-0003-2686-4627"]},"institutions":[{"id":"https://openalex.org/I21256249","display_name":"Tashkent University of Information Technology","ror":"https://ror.org/05987a729","country_code":"UZ","type":"education","lineage":["https://openalex.org/I21256249"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Shokhrukhmirzo Kholdorov","raw_affiliation_strings":["TUIT named after Mukhammad al-Khwarizmi,Department of robotics and intelligent systems,Tashkent,Uzbekistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TUIT named after Mukhammad al-Khwarizmi,Department of robotics and intelligent systems,Tashkent,Uzbekistan","institution_ids":["https://openalex.org/I21256249"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146733433","display_name":"Karimova Maftuna","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I21256249","display_name":"Tashkent University of Information Technology","ror":"https://ror.org/05987a729","country_code":"UZ","type":"education","lineage":["https://openalex.org/I21256249"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Maftuna Karimova","raw_affiliation_strings":["TUIT named after Mukhammad al-Khwarizmi,Department of robotics and intelligent systems,Tashkent,Uzbekistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TUIT named after Mukhammad al-Khwarizmi,Department of robotics and intelligent systems,Tashkent,Uzbekistan","institution_ids":["https://openalex.org/I21256249"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123437575","display_name":"Lutfulla Murodjonov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I21256249","display_name":"Tashkent University of Information Technology","ror":"https://ror.org/05987a729","country_code":"UZ","type":"education","lineage":["https://openalex.org/I21256249"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Lutfulla Murodjonov","raw_affiliation_strings":["TUIT named after Mukhammad al-Khwarizmi,Department of robotics and intelligent systems,Tashkent,Uzbekistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TUIT named after Mukhammad al-Khwarizmi,Department of robotics and intelligent systems,Tashkent,Uzbekistan","institution_ids":["https://openalex.org/I21256249"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I21256249"],"apc_list":null,"apc_paid":null,"fwci":0.3567,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54602513,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"988","last_page":"992"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9932000041007996,"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":0.9932000041007996,"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":0.004399999976158142,"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":0.0006000000284984708,"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/speaker-diarization","display_name":"speaker diarization","score":0.8889999985694885},{"id":"https://openalex.org/keywords/prosodic-features","display_name":"prosodic features","score":0.859000027179718},{"id":"https://openalex.org/keywords/ecapa-tdnn","display_name":"ECAPA-TDNN","score":0.7490000128746033},{"id":"https://openalex.org/keywords/deep-embedding","display_name":"deep embedding","score":0.5130000114440918},{"id":"https://openalex.org/keywords/emotional-speech","display_name":"emotional speech","score":0.6399999856948853},{"id":"https://openalex.org/keywords/speaker-embedding","display_name":"speaker embedding","score":0.5009999871253967},{"id":"https://openalex.org/keywords/real-time-systems","display_name":"real-time systems","score":0.4740000069141388}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8873000144958496},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7404999732971191},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7163000106811523},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.49939998984336853},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4424999952316284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4090000092983246},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.32280001044273376},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.3199999928474426},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2782999873161316},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icaaic64647.2025.11330488","doi":"https://doi.org/10.1109/icaaic64647.2025.11330488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaaic64647.2025.11330488","pdf_url":null,"source":{"id":"https://openalex.org/S4363607845","display_name":"International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 4th International Conference on Applied Artificial Intelligence and Computing (ICAAIC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2081074144","https://openalex.org/W2138368989","https://openalex.org/W2890964092","https://openalex.org/W2938358845","https://openalex.org/W3006475563","https://openalex.org/W3024869864","https://openalex.org/W3134322125","https://openalex.org/W3143367551","https://openalex.org/W3182700327","https://openalex.org/W3199096436","https://openalex.org/W4206748919","https://openalex.org/W4293483492","https://openalex.org/W4364321301","https://openalex.org/W4383374918","https://openalex.org/W4387672237","https://openalex.org/W4391021638","https://openalex.org/W4407376462"],"related_works":["https://openalex.org/W3151768066","https://openalex.org/W3143367551","https://openalex.org/W3024085187","https://openalex.org/W4245862033","https://openalex.org/W2101025008","https://openalex.org/W4385823101","https://openalex.org/W2164512637","https://openalex.org/W4392973202","https://openalex.org/W2021300257","https://openalex.org/W4387364168"],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,43,75],"is":[2,45],"the":[3,48,59,62,70,72,78,82],"process":[4],"of":[5,61,81],"identifying":[6],"speech":[7,35],"segments":[8],"in":[9,33,65,103],"an":[10,40],"audio":[11],"stream":[12],"and":[13,99],"assigning":[14],"them":[15],"to":[16,89],"a":[17,66],"specific":[18],"speaker.":[19],"Since":[20],"classical":[21],"systems":[22],"do":[23],"not":[24],"take":[25],"into":[26],"account":[27],"prosodic":[28,50,54],"features,":[29],"their":[30],"accuracy":[31],"decreases":[32],"emotional":[34],"situations.":[36],"In":[37,47,69,92],"this":[38],"study,":[39,71],"emotion-sensitive":[41,73],"speaker":[42,74],"system":[44],"proposed.":[46],"model,":[49],"vectors":[51],"derived":[52],"from":[53,86],"features":[55],"are":[56],"combined":[57],"with":[58],"embeddings":[60],"ECAPA-TDNN":[63],"model":[64,76,85],"modulation":[67],"manner.":[68],"reduced":[77],"DER":[79],"performance":[80],"simple":[83],"baseline":[84],"11.6":[87],"%":[88],"7.9":[90],"%.":[91],"addition,":[93],"it":[94],"has":[95],"low":[96],"computational":[97],"costs":[98],"provides":[100],"significant":[101],"results":[102],"real-time":[104],"systems.":[105]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-01-21T00:00:00"}