{"id":"https://openalex.org/W4200530736","doi":"https://doi.org/10.1145/3461615.3485430","title":"Group-Level Focus of Visual Attention for Improved Active Speaker Detection","display_name":"Group-Level Focus of Visual Attention for Improved Active Speaker Detection","publication_year":2021,"publication_date":"2021-10-18","ids":{"openalex":"https://openalex.org/W4200530736","doi":"https://doi.org/10.1145/3461615.3485430"},"language":"en","primary_location":{"id":"doi:10.1145/3461615.3485430","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3461615.3485430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Publication of the 2021 International Conference on Multimodal Interaction","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/A5083194238","display_name":"Christopher Birmingham","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Christopher Birmingham","raw_affiliation_strings":["Computer Science/Interaction Lab, University of Southern California, United States"],"affiliations":[{"raw_affiliation_string":"Computer Science/Interaction Lab, University of Southern California, United States","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010248533","display_name":"Maja J. Matari\u0107","orcid":"https://orcid.org/0000-0001-8958-6666"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2800817003","display_name":"Southern California University for Professional Studies","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maja Mataric","raw_affiliation_strings":["University of Southern California, United States"],"affiliations":[{"raw_affiliation_string":"University of Southern California, United States","institution_ids":["https://openalex.org/I2800817003","https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081566320","display_name":"Kalin Stefanov","orcid":"https://orcid.org/0000-0002-0861-8660"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Kalin Stefanov","raw_affiliation_strings":["Monash University, Australia"],"affiliations":[{"raw_affiliation_string":"Monash University, Australia","institution_ids":["https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5083194238"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17762001,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"37","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9926999807357788,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.989300012588501,"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":0.8029664158821106},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5970757007598877},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.50374835729599},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4943406581878662},{"id":"https://openalex.org/keywords/situated","display_name":"Situated","score":0.4863448739051819},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.46930602192878723},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44756877422332764},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4173811674118042},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36738884449005127}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8029664158821106},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5970757007598877},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.50374835729599},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4943406581878662},{"id":"https://openalex.org/C132829578","wikidata":"https://www.wikidata.org/wiki/Q581151","display_name":"Situated","level":2,"score":0.4863448739051819},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.46930602192878723},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44756877422332764},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4173811674118042},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36738884449005127},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3461615.3485430","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3461615.3485430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Publication of the 2021 International Conference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G8973986","display_name":null,"funder_award_id":"IIS ? 1925083","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2081074144","https://openalex.org/W2085331248","https://openalex.org/W2090088747","https://openalex.org/W2114032116","https://openalex.org/W2140831887","https://openalex.org/W2159591770","https://openalex.org/W2186222003","https://openalex.org/W2395639500","https://openalex.org/W2596164567","https://openalex.org/W2604292070","https://openalex.org/W2768817490","https://openalex.org/W2884295076","https://openalex.org/W2948435200","https://openalex.org/W3009754773","https://openalex.org/W3089722697","https://openalex.org/W3103806448","https://openalex.org/W3104119587","https://openalex.org/W4253732063"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W2144208207","https://openalex.org/W4389984014","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"This":[0,14],"work":[1],"addresses":[2],"the":[3,68,99,108],"problem":[4],"of":[5,28,70,73,110],"active":[6,35,86,111],"speaker":[7,36,87,112],"detection":[8,37,88],"in":[9,76],"physically":[10],"situated":[11],"multiparty":[12],"interactions.":[13],"challenge":[15],"requires":[16],"a":[17,25,79],"robust":[18],"solution":[19],"that":[20,44,55,98],"can":[21],"perform":[22],"effectively":[23],"across":[24,89],"wide":[26],"range":[27],"speakers":[29,90],"and":[30,91],"physical":[31,51,92],"contexts.":[32,93],"Current":[33],"state-of-the-art":[34,103],"approaches":[38],"rely":[39],"on":[40],"machine":[41],"learning":[42],"methods":[43,57,104],"do":[45,58],"not":[46,59],"generalize":[47],"well":[48,61],"to":[49],"new":[50],"settings.":[52],"We":[53,66],"find":[54],"these":[56],"transfer":[60],"even":[62],"between":[63],"similar":[64],"datasets.":[65],"propose":[67],"use":[69],"group-level":[71],"focus":[72],"visual":[74],"attention":[75],"combination":[77],"with":[78],"general":[80],"audio-video":[81],"synchronizer":[82],"method":[83],"for":[84,107],"improved":[85],"Our":[94],"dataset-independent":[95],"experiments":[96],"demonstrate":[97],"proposed":[100],"approach":[101],"outperforms":[102],"trained":[105],"specifically":[106],"task":[109],"detection.":[113]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}