{"id":"https://openalex.org/W4409723527","doi":"https://doi.org/10.1109/mprv.2025.3550543","title":"VoiceSeeker: Energy-Efficient and Accurate Audio\u2013Visual Target Speaker Separation on Mobile Devices","display_name":"VoiceSeeker: Energy-Efficient and Accurate Audio\u2013Visual Target Speaker Separation on Mobile Devices","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409723527","doi":"https://doi.org/10.1109/mprv.2025.3550543"},"language":"en","primary_location":{"id":"doi:10.1109/mprv.2025.3550543","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mprv.2025.3550543","pdf_url":null,"source":{"id":"https://openalex.org/S24191132","display_name":"IEEE Pervasive Computing","issn_l":"1536-1268","issn":["1536-1268","1558-2590"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Pervasive Computing","raw_type":"journal-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/A5009621491","display_name":"Juheon Yi","orcid":"https://orcid.org/0000-0002-5080-7502"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Juheon Yi","raw_affiliation_strings":["Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051910236","display_name":"Kyungjin Lee","orcid":"https://orcid.org/0000-0002-7120-9595"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyungjin Lee","raw_affiliation_strings":["Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hyunseok Oh","orcid":"https://orcid.org/0009-0000-1413-7313"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunseok Oh","raw_affiliation_strings":["Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114626700","display_name":"Youngki Lee","orcid":"https://orcid.org/0000-0002-1319-7071"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngki Lee","raw_affiliation_strings":["Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5009621491"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08874737,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"24","issue":"1","first_page":"44","last_page":"52"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.98580002784729,"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":0.9846000075340271,"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":0.8638970255851746},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.5283178687095642},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48738032579421997},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4703909158706665},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.46235784888267517},{"id":"https://openalex.org/keywords/ubiquitous-computing","display_name":"Ubiquitous computing","score":0.4600714147090912},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.43610838055610657},{"id":"https://openalex.org/keywords/smartwatch","display_name":"Smartwatch","score":0.42979395389556885},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4297387897968292},{"id":"https://openalex.org/keywords/mobile-computing","display_name":"Mobile computing","score":0.41131266951560974},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3596041798591614},{"id":"https://openalex.org/keywords/wearable-computer","display_name":"Wearable computer","score":0.1800725758075714},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.17016354203224182},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14746832847595215},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09687379002571106}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8638970255851746},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.5283178687095642},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48738032579421997},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4703909158706665},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.46235784888267517},{"id":"https://openalex.org/C172195944","wikidata":"https://www.wikidata.org/wiki/Q541265","display_name":"Ubiquitous computing","level":2,"score":0.4600714147090912},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.43610838055610657},{"id":"https://openalex.org/C29794715","wikidata":"https://www.wikidata.org/wiki/Q5362345","display_name":"Smartwatch","level":3,"score":0.42979395389556885},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4297387897968292},{"id":"https://openalex.org/C144543869","wikidata":"https://www.wikidata.org/wiki/Q2738570","display_name":"Mobile computing","level":2,"score":0.41131266951560974},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3596041798591614},{"id":"https://openalex.org/C150594956","wikidata":"https://www.wikidata.org/wiki/Q1334829","display_name":"Wearable computer","level":2,"score":0.1800725758075714},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.17016354203224182},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14746832847595215},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09687379002571106},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mprv.2025.3550543","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mprv.2025.3550543","pdf_url":null,"source":{"id":"https://openalex.org/S24191132","display_name":"IEEE Pervasive Computing","issn_l":"1536-1268","issn":["1536-1268","1558-2590"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Pervasive Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.8399999737739563}],"awards":[{"id":"https://openalex.org/G2057981749","display_name":null,"funder_award_id":"2022R1A2C3008495","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G2717443326","display_name":null,"funder_award_id":"RS-2024-00463802","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2029199293","https://openalex.org/W2041167114","https://openalex.org/W2164598857","https://openalex.org/W2551572271","https://openalex.org/W2734774145","https://openalex.org/W2952218014","https://openalex.org/W2965289829","https://openalex.org/W3022536434","https://openalex.org/W3024085360","https://openalex.org/W3034552680","https://openalex.org/W3140645045","https://openalex.org/W3157070662","https://openalex.org/W4289665794","https://openalex.org/W4375869129","https://openalex.org/W6754420807","https://openalex.org/W6765865358"],"related_works":["https://openalex.org/W2123086119","https://openalex.org/W2915650030","https://openalex.org/W2094192006","https://openalex.org/W2114035912","https://openalex.org/W2557071829","https://openalex.org/W2543142712","https://openalex.org/W2090498639","https://openalex.org/W2739586290","https://openalex.org/W2884639050","https://openalex.org/W1983217178"],"abstract_inverted_index":{"We":[0,63,117],"present":[1],"<inline-formula":[2,134],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[3,135],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[4,136],"notation=\"LaTeX\">${{\\sf":[5,137],"VoiceSeeker}}$</tex-math></inline-formula>,":[6],"a":[7,99,120],"mobile":[8],"system":[9,40],"that":[10,68],"utilizes":[11],"vision":[12],"as":[13],"complementary":[14],"modality":[15],"to":[16,48,105,141],"separate":[17],"the":[18,23,79,109,113,131],"target":[19,36,132],"speaker\u2019s":[20],"speech":[21],"from":[22],"input":[24,81],"mixture":[25],"audio.":[26],"Despite":[27],"recent":[28],"advances":[29],"in":[30],"deep":[31],"neural":[32],"network":[33],"(DNN)-based":[34],"audio\u2013visual":[35,61,80,87],"speaker":[37],"separation,":[38],"important":[39],"challenges":[41],"remain":[42],"unsolved:":[43],"separation":[44,76,115,123,148],"accuracy":[45],"drop":[46],"due":[47],"visual":[49],"feature":[50],"quality":[51],"fluctuation,":[52],"and":[53,74,111,128,150],"high":[54],"resource":[55],"demand":[56],"of":[57,101,126],"composite-DNN":[58],"execution":[59],"on":[60,78,86,108],"inputs.":[62],"design":[64,98],"an":[65],"adaptive":[66],"pipeline":[67,124],"flexibly":[69],"switches":[70],"between":[71],"audio\u2013visual,":[72],"audio-only,":[73],"no":[75],"depending":[77],"content.":[82],"For":[83],"agile":[84],"adaptation":[85],"inputs":[88],"whose":[89],"content":[90],"changes":[91],"rapidly":[92],"with":[93],"low":[94],"temporal":[95],"correlation,":[96],"we":[97],"suite":[100],"lightweight":[102],"probing":[103],"techniques":[104],"analyze":[106],"them":[107],"fly":[110],"select":[112],"adequate":[114],"path.":[116],"also":[118],"develop":[119],"continuous":[121],"audio-only":[122],"capable":[125],"robustly":[127],"efficiently":[129],"separating":[130],"speaker.":[133],"VoiceSeeker}}$</tex-math></inline-formula>":[138],"achieves":[139],"up":[140],"49%":[142],"energy":[143],"consumption":[144],"reduction,":[145],"2.2":[146],"dB":[147],"accuracy,":[149],"41%":[151],"latency":[152],"gain":[153],"over":[154],"baselines.":[155]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}