{"id":"https://openalex.org/W3097022478","doi":"https://doi.org/10.21437/interspeech.2020-1950","title":"Speaker Attribution with Voice Profiles by Graph-Based Semi-Supervised Learning","display_name":"Speaker Attribution with Voice Profiles by Graph-Based Semi-Supervised Learning","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3097022478","doi":"https://doi.org/10.21437/interspeech.2020-1950","mag":"3097022478"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1950","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1950","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.03634","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063578134","display_name":"Jixuan Wang","orcid":"https://orcid.org/0000-0003-1986-6747"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jixuan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101602536","display_name":"Xiong Xiao","orcid":"https://orcid.org/0009-0001-5128-6518"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiong Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101674460","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0002-3101-7011"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020436837","display_name":"Ranjani Ramamurthy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ranjani Ramamurthy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056256317","display_name":"Frank Rudzicz","orcid":"https://orcid.org/0000-0002-1139-3423"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frank Rudzicz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5012113499","display_name":"Michael Brudno","orcid":"https://orcid.org/0000-0001-7947-2243"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Brudno","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"289","last_page":"293"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.9980000257492065,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9979000091552734,"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":0.7764390707015991},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7176256775856018},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6006491780281067},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5957688689231873},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5099350214004517},{"id":"https://openalex.org/keywords/attribution","display_name":"Attribution","score":0.49160417914390564},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4634115397930145},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4090958535671234},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3406989574432373},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3399808406829834},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.10448536276817322},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06181350350379944}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7764390707015991},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7176256775856018},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6006491780281067},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5957688689231873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5099350214004517},{"id":"https://openalex.org/C143299363","wikidata":"https://www.wikidata.org/wiki/Q900584","display_name":"Attribution","level":2,"score":0.49160417914390564},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4634115397930145},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4090958535671234},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3406989574432373},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3399808406829834},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.10448536276817322},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06181350350379944},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2020-1950","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1950","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.03634","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.03634","pdf_url":"https://arxiv.org/pdf/2102.03634","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.03634","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.03634","pdf_url":"https://arxiv.org/pdf/2102.03634","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1965819578","https://openalex.org/W2038101708","https://openalex.org/W2046056978","https://openalex.org/W2095705004","https://openalex.org/W2104290444","https://openalex.org/W2132914434","https://openalex.org/W2139823104","https://openalex.org/W2150769028","https://openalex.org/W2154455818","https://openalex.org/W2176412452","https://openalex.org/W2407712691","https://openalex.org/W2519887557","https://openalex.org/W2606780347","https://openalex.org/W2612434969","https://openalex.org/W2620757702","https://openalex.org/W2638067502","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2896538040","https://openalex.org/W2918342466","https://openalex.org/W2962788625","https://openalex.org/W2963224980","https://openalex.org/W2963386851","https://openalex.org/W2963470929","https://openalex.org/W2963702081","https://openalex.org/W2999547272","https://openalex.org/W3016021376","https://openalex.org/W4210257598"],"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/W2997340161"],"abstract_inverted_index":{"Speaker":[0,90],"attribution":[1,34,91,131,147],"is":[2,15,47,77],"required":[3],"in":[4],"many":[5],"real-world":[6],"applications,":[7],"such":[8],"as":[9],"meeting":[10,137],"transcription,":[11],"where":[12],"speaker":[13,22,33,85,130,146,157],"identity":[14],"assigned":[16],"to":[17,21,30,120,128,151,154],"each":[18,50,162],"utterance":[19,163],"according":[20],"voice":[23,56],"profiles.":[24],"In":[25],"this":[26],"paper,":[27],"we":[28],"propose":[29],"solve":[31],"the":[32,80,83,122,126,141],"problem":[35,97],"by":[36,60,79,149],"using":[37],"graph-based":[38,103],"semi-supervised":[39,95],"learning":[40,96],"methods.":[41],"A":[42],"graph":[43,111,127,142],"of":[44,73,87,125],"speech":[45,88],"segments":[46,54,64],"built":[48],"for":[49],"session,":[51],"on":[52,98,100,135],"which":[53,101],"from":[55,65],"profiles":[57],"are":[58,68,105,118],"represented":[59],"labeled":[61],"nodes":[62,76],"while":[63],"test":[66],"utterances":[67],"unlabeled":[69],"nodes.":[70],"The":[71,115],"weight":[72],"edges":[74],"between":[75,82],"evaluated":[78],"similarities":[81],"pretrained":[84],"embeddings":[86],"segments.":[89],"then":[92],"becomes":[93],"a":[94,155],"graphs,":[99],"two":[102],"methods":[104],"applied:":[106],"label":[107],"propagation":[108],"(LP)":[109],"and":[110],"neural":[112],"networks":[113],"(GNNs).":[114],"proposed":[116],"approaches":[117,144],"able":[119],"utilize":[121],"structural":[123],"information":[124],"improve":[129],"performance.":[132],"Experimental":[133],"results":[134],"real":[136],"data":[138],"show":[139],"that":[140,160],"based":[143],"reduce":[145],"error":[148],"up":[150],"68%":[152],"compared":[153],"baseline":[156],"identification":[158],"approach":[159],"processes":[161],"independently.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}