{"id":"https://openalex.org/W7123675795","doi":"https://doi.org/10.1109/mmsp64401.2025.11324301","title":"Towards Low-Latency Tracking of Multiple Speakers With Short-Context Speaker Embeddings","display_name":"Towards Low-Latency Tracking of Multiple Speakers With Short-Context Speaker Embeddings","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7123675795","doi":"https://doi.org/10.1109/mmsp64401.2025.11324301"},"language":null,"primary_location":{"id":"doi:10.1109/mmsp64401.2025.11324301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp64401.2025.11324301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Workshop on Multimedia Signal Processing (MMSP)","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/A5119725465","display_name":"Taous Iatariene","orcid":null},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Taous Iatariene","raw_affiliation_strings":["Orange Innovation,Rennes,France"],"affiliations":[{"raw_affiliation_string":"Orange Innovation,Rennes,France","institution_ids":["https://openalex.org/I19370010"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122951592","display_name":"Alexandre Gu\u00e9rin","orcid":null},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Alexandre Gu\u00e9rin","raw_affiliation_strings":["Orange Innovation,Rennes,France"],"affiliations":[{"raw_affiliation_string":"Orange Innovation,Rennes,France","institution_ids":["https://openalex.org/I19370010"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122938031","display_name":"Romain Serizel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Romain Serizel","raw_affiliation_strings":["University de Lorraine, CNRS, Inria, Loria,Nancy,France"],"affiliations":[{"raw_affiliation_string":"University de Lorraine, CNRS, Inria, Loria,Nancy,France","institution_ids":["https://openalex.org/I4210121838","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5119725465"],"corresponding_institution_ids":["https://openalex.org/I19370010"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.69807485,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"246","last_page":"251"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.7408999800682068,"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":0.7408999800682068,"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":0.21789999306201935,"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":0.009399999864399433,"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/embedding","display_name":"Embedding","score":0.7748000025749207},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6837999820709229},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.6697999835014343},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6323000192642212},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5906999707221985},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48820000886917114},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4832000136375427}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7748000025749207},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6985999941825867},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6837999820709229},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.6697999835014343},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6323000192642212},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6233999729156494},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5906999707221985},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48820000886917114},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4832000136375427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44830000400543213},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.39309999346733093},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2678999900817871},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.2676999866962433}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp64401.2025.11324301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp64401.2025.11324301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Workshop on Multimedia Signal Processing (MMSP)","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":22,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1994037893","https://openalex.org/W2046056978","https://openalex.org/W2726515241","https://openalex.org/W2890964092","https://openalex.org/W2893728996","https://openalex.org/W2972705840","https://openalex.org/W3016232124","https://openalex.org/W3021261768","https://openalex.org/W3024869864","https://openalex.org/W3086436251","https://openalex.org/W3096730275","https://openalex.org/W3132830522","https://openalex.org/W3143367551","https://openalex.org/W3197097128","https://openalex.org/W3206110053","https://openalex.org/W4367597591","https://openalex.org/W4375869221","https://openalex.org/W4385823344","https://openalex.org/W4387557508","https://openalex.org/W4388117349","https://openalex.org/W7117309734"],"related_works":[],"abstract_inverted_index":{"Speaker":[0],"embeddings":[1],"are":[2,137],"promising":[3],"identity-related":[4],"features":[5],"that":[6,133,153],"can":[7],"enhance":[8],"the":[9,53,91,95,106],"identity":[10,25,43,65,110,119],"assignment":[11],"performance":[12],"of":[13,55,94,97,108,114],"a":[14,72,124],"tracking":[15,56,129],"system":[16,57],"by":[17,23],"leveraging":[18],"its":[19],"spatial":[20,92],"predictions,":[21],"i.e,":[22],"performing":[24,109],"reassignment.":[26,66],"Common":[27],"speaker":[28,82,87,96,126],"embedding":[29,83,127,141],"extractors":[30],"usually":[31],"struggle":[32],"with":[33],"short":[34,80],"temporal":[35,48],"contexts":[36],"and":[37,143],"overlapping":[38],"speech,":[39],"which":[40,59],"imposes":[41],"long-term":[42],"reassignment":[44,111,150],"to":[45,101,121,146,158],"exploit":[46],"longer":[47],"contexts.":[49],"However,":[50],"this":[51],"increases":[52],"probability":[54],"errors,":[58],"in":[60],"turn":[61],"impacts":[62],"negatively":[63],"on":[64],"To":[67],"address":[68],"this,":[69],"we":[70],"propose":[71],"Knowledge":[73],"Distillation":[74],"(KD)":[75],"based":[76,128],"training":[77],"approach":[78],"for":[79],"context":[81],"extraction":[84,142],"from":[85],"two":[86],"mixtures.":[88],"We":[89,104],"leverage":[90],"information":[93],"interest":[98],"using":[99],"beamforming":[100],"reduce":[102],"overlap.":[103,147],"study":[105],"feasibility":[107],"over":[112],"blocks":[113],"fixed":[115],"size,":[116],"i.e.,":[117],"blockwise":[118,149],"reassignment,":[120],"go":[122],"towards":[123],"low-latency":[125],"system.":[130],"Results":[131],"demonstrate":[132],"our":[134],"distilled":[135],"models":[136],"effective":[138],"at":[139],"short-context":[140],"more":[144,162],"robust":[145],"Although,":[148],"results":[151],"indicate":[152],"further":[154],"work":[155],"is":[156],"needed":[157],"handle":[159],"simultaneous":[160],"speech":[161],"effectively.":[163]},"counts_by_year":[],"updated_date":"2026-01-14T23:44:37.837170","created_date":"2026-01-14T00:00:00"}