{"id":"https://openalex.org/W3109127301","doi":"https://doi.org/10.1109/icassp39728.2021.9414578","title":"Multi-Scale Speaker Diarization with Neural Affinity Score Fusion","display_name":"Multi-Scale Speaker Diarization with Neural Affinity Score Fusion","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3109127301","doi":"https://doi.org/10.1109/icassp39728.2021.9414578","mag":"3109127301"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.10527","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101397880","display_name":"Tae Jin Park","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"]},{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tae Jin Park","raw_affiliation_strings":["University of Southern California","University  of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I2800817003"]},{"raw_affiliation_string":"University  of Southern California","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I2800817003"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101849944","display_name":"Manoj Kumar","orcid":"https://orcid.org/0000-0003-2100-461X"},"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":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manoj Kumar","raw_affiliation_strings":["University of Southern California","University  of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I2800817003"]},{"raw_affiliation_string":"University  of Southern California","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I2800817003"]}]},{"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"]},{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["University of Southern California","University  of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I2800817003"]},{"raw_affiliation_string":"University  of Southern California","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I2800817003"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1465,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.3241834,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"7173","last_page":"7177"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.9980000257492065,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.8629059791564941},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7194352149963379},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6911014914512634},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5688647031784058},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5552807450294495},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5357780456542969},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.49676090478897095},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4835931658744812},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.47466257214546204},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38366609811782837},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37633299827575684}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8629059791564941},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7194352149963379},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6911014914512634},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5688647031784058},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5552807450294495},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5357780456542969},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.49676090478897095},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4835931658744812},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.47466257214546204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38366609811782837},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37633299827575684},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.10527","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.10527","pdf_url":"https://arxiv.org/pdf/2011.10527","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3109127301","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.10527.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2011.10527","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.10527","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/hpzh-5v06","is_oa":true,"landing_page_url":"https://doi.org/10.17023/hpzh-5v06","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":null,"is_oa":false,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.10527","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.10527","pdf_url":"https://arxiv.org/pdf/2011.10527","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"No poverty","id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3109127301.pdf","grobid_xml":"https://content.openalex.org/works/W3109127301.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1482605500","https://openalex.org/W1484181928","https://openalex.org/W1965819578","https://openalex.org/W2038101708","https://openalex.org/W2093499222","https://openalex.org/W2103375217","https://openalex.org/W2113386290","https://openalex.org/W2405970501","https://openalex.org/W2748488820","https://openalex.org/W2889418727","https://openalex.org/W2890964092","https://openalex.org/W2915347754","https://openalex.org/W2916301830","https://openalex.org/W2921428693","https://openalex.org/W2963745998","https://openalex.org/W2963962398","https://openalex.org/W2972446354","https://openalex.org/W2981103786","https://openalex.org/W2997419692","https://openalex.org/W3008849579","https://openalex.org/W3015778863","https://openalex.org/W3016102464","https://openalex.org/W3020953549","https://openalex.org/W3091905774","https://openalex.org/W3105031100","https://openalex.org/W4300666183","https://openalex.org/W6628802092","https://openalex.org/W6628911050","https://openalex.org/W6682042307","https://openalex.org/W6713679436","https://openalex.org/W6768584815","https://openalex.org/W6776715796","https://openalex.org/W6783596713"],"related_works":["https://openalex.org/W3010196324","https://openalex.org/W3164674954","https://openalex.org/W2972346374","https://openalex.org/W2103348173","https://openalex.org/W2534034218","https://openalex.org/W2782767377","https://openalex.org/W3198482860","https://openalex.org/W2162158162","https://openalex.org/W3191883738","https://openalex.org/W3163929126","https://openalex.org/W2753324760","https://openalex.org/W3015678936","https://openalex.org/W3008357631","https://openalex.org/W3182885906","https://openalex.org/W2949526695","https://openalex.org/W2332932830","https://openalex.org/W3137585377","https://openalex.org/W2153801342","https://openalex.org/W2188385754","https://openalex.org/W2164031777"],"abstract_inverted_index":{"Predicting":[0],"the":[1,16,56,62,65,76,93],"speaker\u2019s":[2],"identity":[3],"of":[4,15,26,38,64,72,82],"short":[5,27],"speech":[6,21,28],"segments":[7,29],"in":[8,20,35,41],"human":[9],"dialogue":[10],"has":[11],"been":[12],"considered":[13],"one":[14],"most":[17],"challenging":[18],"problems":[19],"signal":[22],"processing.":[23],"Speaker":[24],"representations":[25,40],"tend":[30],"to":[31],"be":[32],"unreliable,":[33],"resulting":[34],"poor":[36],"fidelity":[37],"speaker":[39,44,66],"tasks":[42],"requiring":[43],"recognition.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49,96],"propose":[50],"an":[51],"unconventional":[52],"method":[53],"that":[54,74,98],"tackles":[55],"trade-off":[57],"between":[58],"temporal":[59,80],"resolution":[60],"and":[61,103],"quality":[63],"representations.":[67],"To":[68],"find":[69],"a":[70,84,108],"set":[71],"weights":[73],"balance":[75],"scores":[77],"from":[78],"multiple":[79],"scales":[81],"segments,":[83],"neural":[85],"affinity":[86],"score":[87],"fusion":[88],"model":[89],"is":[90],"presented.":[91],"Using":[92],"CALLHOME":[94],"dataset,":[95],"show":[97],"our":[99],"proposed":[100],"multi-scale":[101],"segmentation":[102],"integration":[104],"approach":[105],"can":[106],"achieve":[107],"state-of-the-art":[109],"diarization":[110],"performance.":[111]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
