{"id":"https://openalex.org/W4323767349","doi":"https://doi.org/10.1109/access.2023.3254529","title":"Audio-Visual Overlapped Speech Detection for Spontaneous Distant Speech","display_name":"Audio-Visual Overlapped Speech Detection for Spontaneous Distant Speech","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4323767349","doi":"https://doi.org/10.1109/access.2023.3254529"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3254529","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3254529","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2023.3254529","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010710953","display_name":"Minyoung Kyoung","orcid":"https://orcid.org/0009-0006-2814-9386"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minyoung Kyoung","raw_affiliation_strings":["Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0006-2814-9386","affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hyungbae Jeon","orcid":null},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyungbae Jeon","raw_affiliation_strings":["Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103010759","display_name":"Kiyoung Park","orcid":"https://orcid.org/0009-0004-8673-7608"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kiyoung Park","raw_affiliation_strings":["Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I142401562"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I142401562"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.5219,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.58797814,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"11","issue":null,"first_page":"27426","last_page":"27432"},"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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":0.9915000200271606,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8404165506362915},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7503228783607483},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6579488515853882},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5723901987075806},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5258484482765198},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.48880621790885925},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4772453308105469},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.47565075755119324},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4366987645626068},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.410935640335083},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.14795243740081787},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1079234778881073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8404165506362915},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7503228783607483},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6579488515853882},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5723901987075806},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5258484482765198},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.48880621790885925},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4772453308105469},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.47565075755119324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4366987645626068},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.410935640335083},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.14795243740081787},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1079234778881073},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2023.3254529","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3254529","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:877df0adf2224d0ca90686a3096816ef","is_oa":true,"landing_page_url":"https://doaj.org/article/877df0adf2224d0ca90686a3096816ef","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":"IEEE Access, Vol 11, Pp 27426-27432 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3254529","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3254529","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8100000023841858}],"awards":[{"id":"https://openalex.org/G2167096502","display_name":null,"funder_award_id":"MSIT; 2019-0-00004","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G8472331835","display_name":null,"funder_award_id":"2022-0-00989","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2071301891","https://openalex.org/W2402428045","https://openalex.org/W2551572271","https://openalex.org/W2586878855","https://openalex.org/W2745338770","https://openalex.org/W2797412426","https://openalex.org/W2890952074","https://openalex.org/W2898395910","https://openalex.org/W2917987043","https://openalex.org/W2963155035","https://openalex.org/W2965002127","https://openalex.org/W2968071640","https://openalex.org/W3006974783","https://openalex.org/W3015780472","https://openalex.org/W3016176723","https://openalex.org/W3045742579","https://openalex.org/W3109715615","https://openalex.org/W3119418740","https://openalex.org/W3162293946","https://openalex.org/W3172472082","https://openalex.org/W3203236698","https://openalex.org/W4232282348","https://openalex.org/W4288327876","https://openalex.org/W4385245566","https://openalex.org/W6633847657","https://openalex.org/W6764045775","https://openalex.org/W6767164110","https://openalex.org/W6802040705"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2294333436","https://openalex.org/W2547431347","https://openalex.org/W642007152","https://openalex.org/W2131711534","https://openalex.org/W2184127972","https://openalex.org/W2343205865","https://openalex.org/W2341426843","https://openalex.org/W2009814707"],"abstract_inverted_index":{"Although":[0],"advances":[1],"in":[2,16],"deep":[3],"learning":[4],"have":[5],"brought":[6],"remarkable":[7],"improvements":[8],"to":[9,23,71,105],"Overlapped":[10],"Speech":[11],"Detection":[12],"(OSD),":[13],"the":[14,24,73,76,93,107],"performance":[15],"far-field":[17],"environments":[18],"is":[19],"still":[20],"limited":[21],"owing":[22],"lack":[25],"of":[26,75],"real-world":[27,125],"overlapped":[28,135],"speech":[29,68,127,136],"and":[30,51],"a":[31,57,81,87,124],"low":[32],"signal-to-noise":[33],"ratio.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38,55,79,100],"present":[39,101],"an":[40],"end-to-end":[41],"audiovisual":[42],"OSD":[43,83],"system":[44,84],"based":[45,85],"on":[46,86,123],"decision":[47,109],"fusion":[48],"between":[49,96],"audio":[50,61,144],"video":[52,77,82],"modalities.":[53],"Firstly,":[54],"propose":[56],"simple":[58],"yet":[59],"powerful":[60],"data":[62],"augmentation":[63],"method":[64],"for":[65],"spontaneous":[66],"distant":[67,126],"data.":[69],"Secondly,":[70],"maximize":[72],"effectiveness":[74],"modality,":[78],"design":[80],"cross-speaker":[88],"attention":[89,103],"module":[90,104],"that":[91,116],"explores":[92],"visual":[94],"correlation":[95],"multiple":[97],"speakers.":[98],"Lastly,":[99],"cross-modality":[102],"make":[106],"final":[108],"more":[110],"accurate.":[111],"Our":[112],"experimental":[113],"results":[114],"demonstrate":[115],"our":[117,130],"approach":[118,131],"outperforms":[119],"current":[120],"state-of-the-art":[121],"methods":[122],"dataset.":[128],"Moreover,":[129],"can":[132],"robustly":[133],"detect":[134],"when":[137],"compared":[138],"with":[139],"its":[140],"counterpart,":[141],"which":[142],"uses":[143],"modality":[145],"alone.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
