{"id":"https://openalex.org/W2115175902","doi":"https://doi.org/10.1109/icassp.2009.4960522","title":"Multi-modal speaker diarization of real-world meetings using compressed-domain video features","display_name":"Multi-modal speaker diarization of real-world meetings using compressed-domain video features","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2115175902","doi":"https://doi.org/10.1109/icassp.2009.4960522","mag":"2115175902"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960522","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/145993","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062323483","display_name":"Gerald Friedland","orcid":"https://orcid.org/0000-0002-9400-6539"},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gerald Friedland","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA","Int. Computer Science Institute, 1947 Center Street, Suite 600, Berkeley, CA 94704, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]},{"raw_affiliation_string":"Int. Computer Science Institute, 1947 Center Street, Suite 600, Berkeley, CA 94704, USA","institution_ids":["https://openalex.org/I1297971548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061353073","display_name":"Hayley Hung","orcid":"https://orcid.org/0000-0001-9574-5395"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Hayley Hung","raw_affiliation_strings":["IDIAP Research Institute, Martigny, Switzerland","IDIAP Research Institute, Rue Marconi 19, CH-1920 Martigny, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Research Institute, Rue Marconi 19, CH-1920 Martigny, USA#TAB#","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028054905","display_name":"Chuohao Yeo","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chuohao Yeo","raw_affiliation_strings":["Department of EECS, University of California Berkeley, Berkeley, CA, USA","UC Berkeley, Dept. of EECS, CA 94720, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of EECS, University of California Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"UC Berkeley, Dept. of EECS, CA 94720, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.9295,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.9841028,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"2728","issue":null,"first_page":"4069","last_page":"4072"},"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":0.9994000196456909,"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":0.9984999895095825,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.9051955938339233},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8084577322006226},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6965422034263611},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6840783357620239},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6551132202148438},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6231141686439514},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5982198119163513},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5062810182571411},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34861916303634644},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07443755865097046}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9051955938339233},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8084577322006226},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6965422034263611},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6840783357620239},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6551132202148438},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6231141686439514},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5982198119163513},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5062810182571411},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34861916303634644},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07443755865097046},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2009.4960522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960522","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:145993","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/145993","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:145993","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/145993","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2033966334","https://openalex.org/W2036365100","https://openalex.org/W2073711670","https://openalex.org/W2083419499","https://openalex.org/W2099403067","https://openalex.org/W2113386290","https://openalex.org/W2118847468","https://openalex.org/W2125336414","https://openalex.org/W2153801342","https://openalex.org/W2167709189","https://openalex.org/W2306409666","https://openalex.org/W2338994564","https://openalex.org/W6659344013","https://openalex.org/W6678139733","https://openalex.org/W6678809451"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W1556857061"],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,38],"is":[2,53],"originally":[3],"defined":[4],"as":[5,70],"the":[6,60,78],"task":[7],"of":[8,22,59,77,85],"determining":[9],"ldquowho":[10],"spoke":[11],"whenrdquo":[12],"given":[13],"an":[14],"audio":[15],"track":[16],"and":[17,74],"no":[18],"other":[19],"prior":[20],"knowledge":[21],"any":[23],"kind.":[24],"The":[25,51],"following":[26],"article":[27],"shows":[28],"a":[29,35,82,97],"multi-modal":[30],"approach":[31,52],"where":[32],"we":[33],"improve":[34],"state-of-the-art":[36,98],"speaker":[37,90],"system":[39],"by":[40],"combining":[41],"standard":[42],"acoustic":[43],"features":[44],"(MFCCs)":[45],"with":[46],"compressed":[47],"domain":[48],"video":[49],"features.":[50],"evaluated":[54],"on":[55],"over":[56],"4.5":[57],"hours":[58],"publicly":[61],"available":[62],"AMI":[63],"meetings":[64],"dataset":[65],"which":[66],"contains":[67],"challenges":[68],"such":[69],"people":[71],"standing":[72],"up":[73],"walking":[75],"out":[76],"room.":[79],"We":[80],"show":[81],"consistent":[83],"improvement":[84],"about":[86],"34%":[87],"relative":[88],"in":[89],"error":[91],"rate":[92],"(21%":[93],"DER)":[94],"compared":[95],"to":[96],"audio-only":[99],"baseline.":[100]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
