{"id":"https://openalex.org/W341386178","doi":"https://doi.org/10.21437/interspeech.2004-681","title":"Separation of multiple concurrent speeches using audio-visual speaker localization and minimum variance beam-forming","display_name":"Separation of multiple concurrent speeches using audio-visual speaker localization and minimum variance beam-forming","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W341386178","doi":"https://doi.org/10.21437/interspeech.2004-681","mag":"341386178"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-681","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5045861786","display_name":"Changkyu Choi","orcid":"https://orcid.org/0000-0002-1470-8662"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changkyu Choi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073698654","display_name":"Donggeon Kong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Donggeon Kong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086101752","display_name":"Hyoung-Ki Lee","orcid":"https://orcid.org/0000-0001-7206-2081"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyoung-Ki Lee","raw_affiliation_strings":["Samsung"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059525147","display_name":"Sang Min Yoon","orcid":"https://orcid.org/0000-0003-0001-1845"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sang Min Yoon","raw_affiliation_strings":["Samsung"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung","institution_ids":["https://openalex.org/I4210101778"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2301","last_page":"2304"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7763330936431885},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.667380154132843},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6349664926528931},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6203887462615967},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6195387244224548},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5890941023826599},{"id":"https://openalex.org/keywords/minimum-variance-unbiased-estimator","display_name":"Minimum-variance unbiased estimator","score":0.5012955665588379},{"id":"https://openalex.org/keywords/omnidirectional-antenna","display_name":"Omnidirectional antenna","score":0.48534098267555237},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4737171530723572},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.46406254172325134},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4515416622161865},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.43512338399887085},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32139885425567627},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.09708097577095032},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09644973278045654},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09107157588005066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7763330936431885},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.667380154132843},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6349664926528931},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6203887462615967},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6195387244224548},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5890941023826599},{"id":"https://openalex.org/C165646398","wikidata":"https://www.wikidata.org/wiki/Q3755281","display_name":"Minimum-variance unbiased estimator","level":3,"score":0.5012955665588379},{"id":"https://openalex.org/C24027999","wikidata":"https://www.wikidata.org/wiki/Q2176348","display_name":"Omnidirectional antenna","level":3,"score":0.48534098267555237},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4737171530723572},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.46406254172325134},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4515416622161865},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.43512338399887085},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32139885425567627},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.09708097577095032},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09644973278045654},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09107157588005066},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C21822782","wikidata":"https://www.wikidata.org/wiki/Q131214","display_name":"Antenna (radio)","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-681","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5400000214576721,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W169382767","https://openalex.org/W1515932869","https://openalex.org/W1517146827","https://openalex.org/W1558276682","https://openalex.org/W2096329835","https://openalex.org/W2123993331","https://openalex.org/W2140672401","https://openalex.org/W2149734398","https://openalex.org/W2163994287"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2900122540","https://openalex.org/W4240587264","https://openalex.org/W2011788874","https://openalex.org/W2041060376","https://openalex.org/W2963983801","https://openalex.org/W3119734852"],"abstract_inverted_index":{"Speaker":[0],"segmentation":[1],"is":[2,55],"an":[3,23,30,37],"important":[4],"task":[5],"in":[6,15,75],"multi-party":[7],"conversations.":[8],"Overlapping":[9],"speech":[10,25,54],"poses":[11],"a":[12,59,76],"serious":[13],"problem":[14],"segmenting":[16],"audio":[17],"into":[18],"speaker":[19],"turns.":[20],"We":[21],"propose":[22],"audio-visual":[24],"separation":[26],"system":[27,81],"consisting":[28],"of":[29,66,73],"array":[31],"microphone":[32],"with":[33],"eight":[34],"sensors":[35],"and":[36,71],"omnidirectional":[38],"color":[39],"camera.":[40],"Multiple":[41],"concurrent":[42],"speeches":[43],"are":[44],"segmented":[45,53],"by":[46,58],"fusing":[47],"the":[48,79],"two":[49],"heterogeneous":[50],"sensors.":[51],"Each":[52],"further":[56],"enhanced":[57],"linearly":[60],"constrained":[61],"minimum":[62],"variance":[63],"beamformer.":[64],"Regardless":[65],"co-existing":[67],"wide-band":[68],"sound":[69],"sources":[70],"pictures":[72],"human":[74],"reverberant":[77],"environment":[78],"proposed":[80],"effectively":[82],"separates":[83],"multiple":[84],"target":[85],"speeches.":[86]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
