{"id":"https://openalex.org/W2766958920","doi":"https://doi.org/10.1145/3123266.3123338","title":"A Paralinguistic Approach To Speaker Diarisation","display_name":"A Paralinguistic Approach To Speaker Diarisation","publication_year":2017,"publication_date":"2017-10-19","ids":{"openalex":"https://openalex.org/W2766958920","doi":"https://doi.org/10.1145/3123266.3123338","mag":"2766958920"},"language":"en","primary_location":{"id":"doi:10.1145/3123266.3123338","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3123338","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM international conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/3500694","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100333709","display_name":"Yue Zhang","orcid":"https://orcid.org/0000-0002-3823-7674"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yue Zhang","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016747567","display_name":"Felix Weninger","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Felix Weninger","raw_affiliation_strings":["Nuance Communications, Ulm, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications, Ulm, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023229829","display_name":"Boqing Liu","orcid":"https://orcid.org/0000-0001-7987-3979"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Boqing Liu","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019825395","display_name":"Maximilian Schmitt","orcid":"https://orcid.org/0000-0001-7453-5612"},"institutions":[{"id":"https://openalex.org/I186354981","display_name":"University of Passau","ror":"https://ror.org/05ydjnb78","country_code":"DE","type":"education","lineage":["https://openalex.org/I186354981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Maximilian Schmitt","raw_affiliation_strings":["University of Passau, Passau, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Passau, Passau, Germany","institution_ids":["https://openalex.org/I186354981"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023264395","display_name":"Florian Eyben","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Florian Eyben","raw_affiliation_strings":["audEERING GmbH, Gilching, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"audEERING GmbH, Gilching, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn Schuller","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"98","issue":null,"first_page":"387","last_page":"392"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9966999888420105,"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/T10860","display_name":"Speech and Audio Processing","score":0.9962000250816345,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/paralanguage","display_name":"Paralanguage","score":0.9921613335609436},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7122159600257874},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.700211763381958},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6716350317001343},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6473424434661865},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5159988403320312},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.428165465593338},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3451438546180725},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33431708812713623},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3239874243736267},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.128517746925354},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.12526366114616394}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.9921613335609436},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7122159600257874},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.700211763381958},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6716350317001343},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6473424434661865},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5159988403320312},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.428165465593338},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3451438546180725},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33431708812713623},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3239874243736267},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.128517746925354},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.12526366114616394}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3123266.3123338","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3123338","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM international conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:71830","is_oa":false,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/71830","pdf_url":null,"source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"},{"id":"pmh:oai:zenodo.org:3500694","is_oa":true,"landing_page_url":"https://zenodo.org/record/3500694","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:3500694","is_oa":true,"landing_page_url":"https://zenodo.org/record/3500694","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5099999904632568,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W3765491","https://openalex.org/W67702164","https://openalex.org/W142238497","https://openalex.org/W147964346","https://openalex.org/W163811496","https://openalex.org/W304834817","https://openalex.org/W1501506202","https://openalex.org/W1618905105","https://openalex.org/W1971791733","https://openalex.org/W2000436309","https://openalex.org/W2002311796","https://openalex.org/W2004942499","https://openalex.org/W2012316161","https://openalex.org/W2015293542","https://openalex.org/W2041823554","https://openalex.org/W2048681867","https://openalex.org/W2057563799","https://openalex.org/W2064675550","https://openalex.org/W2081074144","https://openalex.org/W2082927806","https://openalex.org/W2090777335","https://openalex.org/W2096465424","https://openalex.org/W2097583714","https://openalex.org/W2111057910","https://openalex.org/W2115257206","https://openalex.org/W2124737236","https://openalex.org/W2133990480","https://openalex.org/W2135636388","https://openalex.org/W2136745572","https://openalex.org/W2144125830","https://openalex.org/W2148613904","https://openalex.org/W2156255174","https://openalex.org/W2159591770","https://openalex.org/W2164512637","https://openalex.org/W2169264834","https://openalex.org/W2169863498","https://openalex.org/W2186645669","https://openalex.org/W2400139865","https://openalex.org/W2402428045","https://openalex.org/W2487211121","https://openalex.org/W2534034218","https://openalex.org/W2620757702","https://openalex.org/W2626961305","https://openalex.org/W2963614358"],"related_works":["https://openalex.org/W1963976507","https://openalex.org/W2206035908","https://openalex.org/W3119288895","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W2185075503","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W2162158162","https://openalex.org/W2019475500"],"abstract_inverted_index":{"In":[0,86],"this":[1],"work,":[2],"we":[3,63],"present":[4],"a":[5,65,87,138,169],"new":[6],"view":[7],"on":[8,18,137],"automatic":[9],"speaker":[10,22,33,71,74,91,103,106,166],"diarisation,":[11],"i.e.,":[12],"assessing":[13],"\"who":[14],"speaks":[15],"when\",":[16],"based":[17],"the":[19,47,79,116,123,147],"recognition":[20],"of":[21,140,172],"traits":[23],"such":[24],"as":[25],"age,":[26],"gender,":[27],"voice":[28,94],"likability,":[29],"and":[30,134],"personality.":[31],"Traditionally,":[32],"diarisation":[34,72,167],"is":[35,98,168],"accomplished":[36],"using":[37,110,162],"low-level":[38],"audio":[39],"descriptors":[40],"(e.g.,":[41],"cepstral":[42],"or":[43],"spectral":[44],"features),":[45],"neglecting":[46],"fact":[48],"that":[49,69,161],"speakers":[50,80],"can":[51],"be":[52],"well":[53],"discriminated":[54],"by":[55,76,93],"humans":[56],"according":[57,81],"to":[58,82,101,122],"various":[59],"perceived":[60],"characteristics.":[61],"Thus,":[62],"advocate":[64],"novel":[66],"paralinguistic":[67,112,163],"approach":[68],"combines":[70],"with":[73],"characterisation":[75],"automatically":[77],"identifying":[78],"their":[83],"individual":[84],"traits.":[85,125],"three-tier":[88],"processing":[89],"flow,":[90],"segmentation":[92],"activity":[95],"detection":[96],"(VAD)":[97],"initially":[99],"performed":[100],"detect":[102],"turns.":[104],"Next,":[105],"attributes":[107],"are":[108,120],"predicted":[109,124],"pre-trained":[111],"models.":[113],"To":[114],"tag":[115],"speakers,":[117],"clustering":[118],"algorithms":[119],"applied":[121],"We":[126],"evaluate":[127],"our":[128],"methods":[129],"against":[130],"state-of-the-art":[131],"open":[132],"source":[133],"commercial":[135],"systems":[136],"corpus":[139],"realistic,":[141],"spontaneous":[142],"dyadic":[143],"conversations":[144],"recorded":[145],"in":[146],"wild":[148],"from":[149],"three":[150],"different":[151],"cultures":[152],"(Chinese,":[153],"English,":[154],"German).":[155],"Our":[156],"results":[157],"provide":[158],"clear":[159],"evidence":[160],"features":[164],"for":[165],"promising":[170],"avenue":[171],"research.":[173]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}