{"id":"https://openalex.org/W4408154964","doi":"https://doi.org/10.3390/bdcc9030059","title":"Comparative Analysis of Audio Feature Extraction for Real-Time Talking Portrait Synthesis","display_name":"Comparative Analysis of Audio Feature Extraction for Real-Time Talking Portrait Synthesis","publication_year":2025,"publication_date":"2025-03-04","ids":{"openalex":"https://openalex.org/W4408154964","doi":"https://doi.org/10.3390/bdcc9030059"},"language":"en","primary_location":{"id":"doi:10.3390/bdcc9030059","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc9030059","pdf_url":"https://www.mdpi.com/2504-2289/9/3/59/pdf?version=1741052699","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-2289/9/3/59/pdf?version=1741052699","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019388564","display_name":"Pegah Salehi","orcid":"https://orcid.org/0000-0002-9149-3829"},"institutions":[{"id":"https://openalex.org/I4210153474","display_name":"Simula Metropolitan Center for Digital Engineering","ror":"https://ror.org/04xtarr15","country_code":"NO","type":"nonprofit","lineage":["https://openalex.org/I184531372","https://openalex.org/I2799829267","https://openalex.org/I4210153474"]},{"id":"https://openalex.org/I78037679","display_name":"UiT The Arctic University of Norway","ror":"https://ror.org/00wge5k78","country_code":"NO","type":"education","lineage":["https://openalex.org/I78037679"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Pegah Salehi","raw_affiliation_strings":["Department of Computer Science, UiT The Arctic University of Norway, 9019 Troms\u00f8, Norway","SimulaMet, 0167 Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0002-9149-3829","affiliations":[{"raw_affiliation_string":"Department of Computer Science, UiT The Arctic University of Norway, 9019 Troms\u00f8, Norway","institution_ids":["https://openalex.org/I78037679"]},{"raw_affiliation_string":"SimulaMet, 0167 Oslo, Norway","institution_ids":["https://openalex.org/I4210153474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073046959","display_name":"Sajad Amouei Sheshkal","orcid":"https://orcid.org/0009-0007-1805-7880"},"institutions":[{"id":"https://openalex.org/I4210153474","display_name":"Simula Metropolitan Center for Digital Engineering","ror":"https://ror.org/04xtarr15","country_code":"NO","type":"nonprofit","lineage":["https://openalex.org/I184531372","https://openalex.org/I2799829267","https://openalex.org/I4210153474"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Sajad Amouei Sheshkal","raw_affiliation_strings":["SimulaMet, 0167 Oslo, Norway"],"raw_orcid":"https://orcid.org/0009-0007-1805-7880","affiliations":[{"raw_affiliation_string":"SimulaMet, 0167 Oslo, Norway","institution_ids":["https://openalex.org/I4210153474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016095767","display_name":"Vajira Thambawita","orcid":"https://orcid.org/0000-0001-6026-0929"},"institutions":[{"id":"https://openalex.org/I4210153474","display_name":"Simula Metropolitan Center for Digital Engineering","ror":"https://ror.org/04xtarr15","country_code":"NO","type":"nonprofit","lineage":["https://openalex.org/I184531372","https://openalex.org/I2799829267","https://openalex.org/I4210153474"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Vajira Thambawita","raw_affiliation_strings":["SimulaMet, 0167 Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0001-6026-0929","affiliations":[{"raw_affiliation_string":"SimulaMet, 0167 Oslo, Norway","institution_ids":["https://openalex.org/I4210153474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089611382","display_name":"Sushant Gautam","orcid":"https://orcid.org/0000-0001-9232-2661"},"institutions":[{"id":"https://openalex.org/I4210153474","display_name":"Simula Metropolitan Center for Digital Engineering","ror":"https://ror.org/04xtarr15","country_code":"NO","type":"nonprofit","lineage":["https://openalex.org/I184531372","https://openalex.org/I2799829267","https://openalex.org/I4210153474"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Sushant Gautam","raw_affiliation_strings":["SimulaMet, 0167 Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0001-9232-2661","affiliations":[{"raw_affiliation_string":"SimulaMet, 0167 Oslo, Norway","institution_ids":["https://openalex.org/I4210153474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019910849","display_name":"Saeed Shafiee Sabet","orcid":"https://orcid.org/0000-0001-5348-8546"},"institutions":[{"id":"https://openalex.org/I4210132524","display_name":"ForzaSys (Norway)","ror":"https://ror.org/02zhfb961","country_code":"NO","type":"company","lineage":["https://openalex.org/I4210132524"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Saeed S. Sabet","raw_affiliation_strings":["Forzasys AS, 0840 Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0001-5348-8546","affiliations":[{"raw_affiliation_string":"Forzasys AS, 0840 Oslo, Norway","institution_ids":["https://openalex.org/I4210132524"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002487909","display_name":"Dag Johansen","orcid":"https://orcid.org/0000-0001-7067-6477"},"institutions":[{"id":"https://openalex.org/I78037679","display_name":"UiT The Arctic University of Norway","ror":"https://ror.org/00wge5k78","country_code":"NO","type":"education","lineage":["https://openalex.org/I78037679"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Dag Johansen","raw_affiliation_strings":["Department of Computer Science, UiT The Arctic University of Norway, 9019 Troms\u00f8, Norway"],"raw_orcid":"https://orcid.org/0000-0001-7067-6477","affiliations":[{"raw_affiliation_string":"Department of Computer Science, UiT The Arctic University of Norway, 9019 Troms\u00f8, Norway","institution_ids":["https://openalex.org/I78037679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102968267","display_name":"Michael A. Riegler","orcid":"https://orcid.org/0000-0002-3153-2064"},"institutions":[{"id":"https://openalex.org/I2799829267","display_name":"Simula Research Laboratory","ror":"https://ror.org/00vn06n10","country_code":"NO","type":"facility","lineage":["https://openalex.org/I2799829267"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Michael A. Riegler","raw_affiliation_strings":["Simula Research Laboratory, 0164 Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0002-3153-2064","affiliations":[{"raw_affiliation_string":"Simula Research Laboratory, 0164 Oslo, Norway","institution_ids":["https://openalex.org/I2799829267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088962741","display_name":"P\u00e5l Halvorsen","orcid":"https://orcid.org/0000-0003-2073-7029"},"institutions":[{"id":"https://openalex.org/I184531372","display_name":"OsloMet \u2013 Oslo Metropolitan University","ror":"https://ror.org/04q12yn84","country_code":"NO","type":"education","lineage":["https://openalex.org/I184531372"]},{"id":"https://openalex.org/I4210153474","display_name":"Simula Metropolitan Center for Digital Engineering","ror":"https://ror.org/04xtarr15","country_code":"NO","type":"nonprofit","lineage":["https://openalex.org/I184531372","https://openalex.org/I2799829267","https://openalex.org/I4210153474"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"P\u00e5l Halvorsen","raw_affiliation_strings":["Faculty of Technology, Art, and Design, Department of Computer Science (IT), Oslo Metropolitan University (OsloMet), 0130 Oslo, Norway","SimulaMet, 0167 Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0003-2073-7029","affiliations":[{"raw_affiliation_string":"Faculty of Technology, Art, and Design, Department of Computer Science (IT), Oslo Metropolitan University (OsloMet), 0130 Oslo, Norway","institution_ids":["https://openalex.org/I184531372"]},{"raw_affiliation_string":"SimulaMet, 0167 Oslo, Norway","institution_ids":["https://openalex.org/I4210153474"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5019388564"],"corresponding_institution_ids":["https://openalex.org/I4210153474","https://openalex.org/I78037679"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02634356,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":"3","first_page":"59","last_page":"59"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9987000226974487,"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":0.9970999956130981,"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/portrait","display_name":"Portrait","score":0.7841129899024963},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5709692239761353},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5507647395133972},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4689343273639679},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.42782527208328247},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4255133867263794},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3598763346672058},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.34634265303611755},{"id":"https://openalex.org/keywords/art-history","display_name":"Art history","score":0.22671273350715637},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1067182719707489},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.062004536390304565},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.05998331308364868}],"concepts":[{"id":"https://openalex.org/C162462552","wikidata":"https://www.wikidata.org/wiki/Q134307","display_name":"Portrait","level":2,"score":0.7841129899024963},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5709692239761353},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5507647395133972},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4689343273639679},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.42782527208328247},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4255133867263794},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3598763346672058},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.34634265303611755},{"id":"https://openalex.org/C52119013","wikidata":"https://www.wikidata.org/wiki/Q50637","display_name":"Art history","level":1,"score":0.22671273350715637},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1067182719707489},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.062004536390304565},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.05998331308364868},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/bdcc9030059","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc9030059","pdf_url":"https://www.mdpi.com/2504-2289/9/3/59/pdf?version=1741052699","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:bc1d06f057ff423ba1d67fdff3ec3687","is_oa":true,"landing_page_url":"https://doaj.org/article/bc1d06f057ff423ba1d67fdff3ec3687","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Big Data and Cognitive Computing, Vol 9, Iss 3, p 59 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/bdcc9030059","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc9030059","pdf_url":"https://www.mdpi.com/2504-2289/9/3/59/pdf?version=1741052699","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8382198595","display_name":null,"funder_award_id":"#314690","funder_id":"https://openalex.org/F4320323299","funder_display_name":"Norges Forskningsr\u00e5d"}],"funders":[{"id":"https://openalex.org/F4320323299","display_name":"Norges Forskningsr\u00e5d","ror":"https://ror.org/00epmv149"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4408154964.pdf"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W139318871","https://openalex.org/W1494198834","https://openalex.org/W1851686334","https://openalex.org/W2103249953","https://openalex.org/W2124509324","https://openalex.org/W2131774270","https://openalex.org/W2175420983","https://openalex.org/W2193413348","https://openalex.org/W2395639500","https://openalex.org/W2536863175","https://openalex.org/W2614986935","https://openalex.org/W2616137712","https://openalex.org/W2793048903","https://openalex.org/W2962785568","https://openalex.org/W2963081548","https://openalex.org/W2995181338","https://openalex.org/W3000442796","https://openalex.org/W3011411500","https://openalex.org/W3016011332","https://openalex.org/W3029186289","https://openalex.org/W3036601975","https://openalex.org/W3039587732","https://openalex.org/W3097792222","https://openalex.org/W3139130199","https://openalex.org/W3160799772","https://openalex.org/W3211147706","https://openalex.org/W4200150166","https://openalex.org/W4200174933","https://openalex.org/W4235562789","https://openalex.org/W4250903264","https://openalex.org/W4281650626","https://openalex.org/W4283520499","https://openalex.org/W4301206121","https://openalex.org/W4311000453","https://openalex.org/W4382777461","https://openalex.org/W4385318467","https://openalex.org/W4390872116","https://openalex.org/W4391708057","https://openalex.org/W4392974949","https://openalex.org/W4400524955","https://openalex.org/W4401507490","https://openalex.org/W4403792004","https://openalex.org/W6765779288","https://openalex.org/W6772922406","https://openalex.org/W6780218876","https://openalex.org/W6792452179","https://openalex.org/W7034400414"],"related_works":["https://openalex.org/W2063032739","https://openalex.org/W2360001249","https://openalex.org/W594086971","https://openalex.org/W2315550989","https://openalex.org/W2031725242","https://openalex.org/W3169920643","https://openalex.org/W2141684174","https://openalex.org/W27177127","https://openalex.org/W4383739071","https://openalex.org/W2358709380"],"abstract_inverted_index":{"This":[0],"paper":[1],"explores":[2],"advancements":[3,121],"in":[4,12,24,85],"real-time":[5,25,63],"talking-head":[6,90],"generation,":[7],"focusing":[8],"on":[9],"overcoming":[10],"challenges":[11],"Audio":[13],"Feature":[14],"Extraction":[15],"(AFE),":[16],"which":[17],"often":[18],"introduces":[19],"latency":[20],"and":[21,33,53,88,126,136],"limits":[22],"responsiveness":[23],"applications.":[26],"To":[27],"address":[28],"these":[29],"issues,":[30],"we":[31],"propose":[32],"implement":[34],"a":[35,98],"fully":[36],"integrated":[37],"system":[38,56],"that":[39,70],"replaces":[40],"conventional":[41],"AFE":[42],"models":[43,64],"with":[44],"OpenAI\u2019s":[45],"Whisper,":[46],"leveraging":[47],"its":[48],"encoder":[49],"to":[50],"optimize":[51],"processing":[52,75],"improve":[54],"overall":[55],"efficiency.":[57],"Our":[58],"evaluation":[59],"of":[60,81,104,110,130],"two":[61],"open-source":[62],"across":[65],"three":[66],"different":[67],"datasets":[68],"shows":[69],"Whisper":[71],"not":[72],"only":[73],"accelerates":[74],"but":[76],"also":[77],"improves":[78],"specific":[79],"aspects":[80],"rendering":[82],"quality,":[83],"resulting":[84],"more":[86,123],"realistic":[87],"responsive":[89,117],"interactions.":[91],"Although":[92],"interviewer":[93],"training":[94,138],"systems":[95],"are":[96],"considered":[97],"potential":[99],"application,":[100],"the":[101,108,111,128],"primary":[102],"contribution":[103],"this":[105],"work":[106],"is":[107],"improvement":[109],"technical":[112],"foundations":[113],"necessary":[114],"for":[115],"creating":[116],"AI":[118],"avatars.":[119],"These":[120],"enable":[122],"immersive":[124],"interactions":[125],"expand":[127],"scope":[129],"AI-driven":[131],"applications,":[132],"including":[133],"educational":[134],"tools":[135],"simulated":[137],"environments.":[139]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
