{"id":"https://openalex.org/W4415709536","doi":"https://doi.org/10.1109/icme59968.2025.11209435","title":"MoMuSE: Momentum Multi-modal Target Speaker Extraction for Real-time Scenarios with Impaired Visual Cues","display_name":"MoMuSE: Momentum Multi-modal Target Speaker Extraction for Real-time Scenarios with Impaired Visual Cues","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415709536","doi":"https://doi.org/10.1109/icme59968.2025.11209435"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209435","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209435","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100367662","display_name":"Junjie Li","orcid":"https://orcid.org/0000-0002-9107-5563"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Junjie Li","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering,Hong Kong SAR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering,Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100643115","display_name":"Ke Zhang","orcid":"https://orcid.org/0000-0002-2536-6426"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Zhang","raw_affiliation_strings":["Shenzhen Research Institute of Big Data,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data,Shenzhen,China","institution_ids":["https://openalex.org/I4210099586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328340","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0003-1523-9631"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["Shenzhen Research Institute of Big Data,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data,Shenzhen,China","institution_ids":["https://openalex.org/I4210099586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004287909","display_name":"Kong Aik Lee","orcid":"https://orcid.org/0000-0001-9133-3000"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kong Aik Lee","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering,Hong Kong SAR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering,Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068768998","display_name":"Man\u2010Wai Mak","orcid":"https://orcid.org/0000-0001-8854-3760"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Man-Wai Mak","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering,Hong Kong SAR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering,Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Shenzhen Research Institute of Big Data,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data,Shenzhen,China","institution_ids":["https://openalex.org/I4210099586"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.949999988079071,"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":0.949999988079071,"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":0.026399999856948853,"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/T11448","display_name":"Face recognition and analysis","score":0.004600000102072954,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5411999821662903},{"id":"https://openalex.org/keywords/sensory-cue","display_name":"Sensory cue","score":0.5164999961853027},{"id":"https://openalex.org/keywords/momentum","display_name":"Momentum (technical analysis)","score":0.48500001430511475},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.44600000977516174},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3675000071525574},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.36410000920295715},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.361299991607666},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.34040001034736633}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6917999982833862},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6173999905586243},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5411999821662903},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.5164999961853027},{"id":"https://openalex.org/C60718061","wikidata":"https://www.wikidata.org/wiki/Q1414747","display_name":"Momentum (technical analysis)","level":2,"score":0.48500001430511475},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.44600000977516174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4153999984264374},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3675000071525574},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.36410000920295715},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.34040001034736633},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3203999996185303},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2727999985218048},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.25529998540878296},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.25110000371932983},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209435","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209435","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2105482032","https://openalex.org/W2127851351","https://openalex.org/W2141998673","https://openalex.org/W2799930831","https://openalex.org/W2808631503","https://openalex.org/W2910254446","https://openalex.org/W2952218014","https://openalex.org/W2972513594","https://openalex.org/W2972568703","https://openalex.org/W3015785290","https://openalex.org/W3015791137","https://openalex.org/W3016048045","https://openalex.org/W3024147341","https://openalex.org/W3148386121","https://openalex.org/W3160658686","https://openalex.org/W3163287738","https://openalex.org/W3182657421","https://openalex.org/W3196570692","https://openalex.org/W4224920251","https://openalex.org/W4364323053","https://openalex.org/W4375869294","https://openalex.org/W4385822249","https://openalex.org/W4392903720","https://openalex.org/W4392909318","https://openalex.org/W4400579920","https://openalex.org/W4401416441","https://openalex.org/W4402112342","https://openalex.org/W4402112488","https://openalex.org/W4402592606","https://openalex.org/W4406208517","https://openalex.org/W4408352717"],"related_works":[],"abstract_inverted_index":{"Audio-visual":[0],"Target":[1],"Speaker":[2,69],"Extraction":[3,70],"(AV-TSE)":[4],"aims":[5],"to":[6,33,83],"isolate":[7],"the":[8,38,54,65,81,86,95],"speech":[9,97],"of":[10,40,124],"a":[11,74],"specific":[12],"target":[13,55,68,87],"speaker":[14,56,75,108],"from":[15,101],"an":[16],"audio":[17],"mixture":[18],"using":[19],"time-synchronized":[20],"visual":[21,26,103,125],"cues.":[22,126],"In":[23,60],"real-world":[24],"scenarios,":[25],"cues":[27,104],"are":[28],"not":[29,58],"always":[30],"available":[31],"due":[32],"various":[34],"impairments,":[35],"which":[36,72],"undermines":[37],"stability":[39],"AV-TSE.":[41],"Despite":[42],"this":[43,61],"challenge,":[44],"humans":[45],"can":[46],"maintain":[47],"attentional":[48],"momentum":[49,77],"over":[50],"time,":[51],"even":[52],"when":[53],"is":[57],"visible.":[59],"paper,":[62],"we":[63],"introduce":[64],"Momentum":[66],"Multi-modal":[67],"(MoMuSE),":[71],"retains":[73],"identity":[76],"in":[78,119],"memory,":[79],"enabling":[80],"model":[82],"continuously":[84],"track":[85],"speaker.":[88],"Designed":[89],"for":[90],"real-time":[91],"inference,":[92],"MoMuSE":[93,114],"extracts":[94],"current":[96],"window":[98],"with":[99,121],"guidance":[100],"both":[102],"and":[105],"dynamically":[106],"updated":[107],"momentum.":[109],"Experimental":[110],"results":[111],"demonstrate":[112],"that":[113],"exhibits":[115],"significant":[116],"improvement,":[117],"particularly":[118],"scenarios":[120],"severe":[122],"impairment":[123]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}