{"id":"https://openalex.org/W4392904074","doi":"https://doi.org/10.1109/icassp48485.2024.10447515","title":"Audio-Visual Child-Adult Speaker Classification in Dyadic Interactions","display_name":"Audio-Visual Child-Adult Speaker Classification in Dyadic Interactions","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904074","doi":"https://doi.org/10.1109/icassp48485.2024.10447515"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447515","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5030974769","display_name":"Anfeng Xu","orcid":"https://orcid.org/0000-0002-4149-3919"},"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":false,"raw_author_name":"Anfeng Xu","raw_affiliation_strings":["University of Southern California,Los Angeles,CA,USA","University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062032121","display_name":"Kevin Huang","orcid":"https://orcid.org/0000-0002-0300-9911"},"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":false,"raw_author_name":"Kevin Huang","raw_affiliation_strings":["University of Southern California,Los Angeles,CA,USA","University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100567944","display_name":"Tiantian Feng","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":false,"raw_author_name":"Tiantian Feng","raw_affiliation_strings":["University of Southern California,Los Angeles,CA,USA","University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049663620","display_name":"Helen Tager\u2010Flusberg","orcid":"https://orcid.org/0000-0002-8768-5414"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Helen Tager-Flusberg","raw_affiliation_strings":["Boston University,Boston,MA,USA","Boston University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University,Boston,MA,USA","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Boston University, Boston, MA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"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":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["University of Southern California,Los Angeles,CA,USA","University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6114,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61285707,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"8090","last_page":"8094"},"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":0.9991000294685364,"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":0.9987000226974487,"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":0.7382982969284058},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6513165235519409},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6167304515838623},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5298827886581421},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5216907858848572},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.517396092414856},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4888705611228943},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.47605061531066895},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33554622530937195}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7382982969284058},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6513165235519409},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6167304515838623},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5298827886581421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5216907858848572},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.517396092414856},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4888705611228943},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.47605061531066895},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33554622530937195},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447515","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320317469","display_name":"Apple","ror":"https://ror.org/059hsda18"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2099001231","https://openalex.org/W2194775991","https://openalex.org/W2587126577","https://openalex.org/W2889288729","https://openalex.org/W2913959566","https://openalex.org/W2963307811","https://openalex.org/W2979826702","https://openalex.org/W2993662639","https://openalex.org/W3015337773","https://openalex.org/W3016098309","https://openalex.org/W3084704861","https://openalex.org/W3094502228","https://openalex.org/W3120485916","https://openalex.org/W3209984917","https://openalex.org/W4214554112","https://openalex.org/W4229440279","https://openalex.org/W4313233335","https://openalex.org/W4360600181","https://openalex.org/W4385822468","https://openalex.org/W4385823034","https://openalex.org/W4386075783","https://openalex.org/W6784333009","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2351687372","https://openalex.org/W2004087835","https://openalex.org/W2314871050"],"abstract_inverted_index":{"Interactions":[0],"involving":[1],"children":[2],"span":[3],"a":[4,51,124],"wide":[5],"range":[6],"of":[7,20,83,115,134,141],"important":[8],"domains":[9],"from":[10,120],"learning":[11],"to":[12,28,47],"clinical":[13],"diagnostic":[14],"and":[15,32,35,39,99,112,132,143,152],"therapeutic":[16],"contexts.":[17],"Automated":[18],"analyses":[19],"such":[21,55,75],"interactions":[22],"are":[23,155],"motivated":[24],"by":[25],"the":[26,43,48,81,130,135],"need":[27],"seek":[29],"accurate":[30],"insights":[31],"offer":[33],"scale":[34],"robustness":[36,133],"across":[37],"diverse":[38],"wide-ranging":[40],"conditions.":[41],"Identifying":[42],"speech":[44,72],"segments":[45],"belonging":[46],"child":[49],"is":[50],"critical":[52],"step":[53],"in":[54,145],"modeling.":[56],"Conventional":[57],"child-adult":[58,86,109],"speaker":[59,87,97,110],"classification":[60,88,127],"typically":[61],"relies":[62],"on":[63,80],"audio":[64],"modeling":[65],"approaches,":[66],"overlooking":[67],"visual":[68,93,100],"signals":[69],"that":[70,123],"convey":[71],"articulation":[73],"information,":[74],"as":[76],"lip":[77],"motion.":[78],"Building":[79],"foundation":[82],"an":[84],"audio-only":[85],"pipeline,":[89],"we":[90],"propose":[91],"incorporating":[92],"cues":[94],"through":[95],"active":[96],"detection":[98],"processing":[101],"models.":[102],"Our":[103],"framework":[104],"involves":[105],"video":[106],"preprocessing,":[107],"utterance-level":[108],"detection,":[111],"late":[113],"fusion":[114],"modality-specific":[116],"predictions.":[117],"We":[118,137],"demonstrate":[119],"extensive":[121],"experiments":[122],"visually":[125],"aided":[126],"pipeline":[128],"enhances":[129],"accuracy":[131],"classification.":[136],"show":[138],"relative":[139],"improvements":[140],"2.38%":[142],"3.97%":[144],"F1":[146],"macro":[147],"score":[148],"when":[149],"one":[150],"face":[151],"two":[153],"faces":[154],"visible,":[156],"respectively.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
