{"id":"https://openalex.org/W2069642050","doi":"https://doi.org/10.1109/icassp.2013.6639170","title":"Where are the challenges in speaker diarization?","display_name":"Where are the challenges in speaker diarization?","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2069642050","doi":"https://doi.org/10.1109/icassp.2013.6639170","mag":"2069642050"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639170","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5047401054","display_name":"Mark Sinclair","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark Sinclair","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, UK","Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, UK","Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7741","last_page":"7745"},"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":0.9980000257492065,"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"}},{"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.9245461225509644},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.7475900650024414},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.743087887763977},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6234622001647949},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5938701033592224},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4824298322200775},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.46334490180015564}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9245461225509644},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.7475900650024414},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.743087887763977},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6234622001647949},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5938701033592224},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4824298322200775},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.46334490180015564},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6639170","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.294.2897","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.294.2897","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.inf.ed.ac.uk/downloads/publications/2013/3512.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4055593462","display_name":null,"funder_award_id":"EP/I031022/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W41021157","https://openalex.org/W2060656758","https://openalex.org/W2081074144","https://openalex.org/W2106015547","https://openalex.org/W2106103082","https://openalex.org/W2115130489","https://openalex.org/W2134309369","https://openalex.org/W2136032552","https://openalex.org/W2137178960","https://openalex.org/W2147520277","https://openalex.org/W2153842971","https://openalex.org/W6675718704","https://openalex.org/W6682756210"],"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":{"We":[0,83],"present":[1],"a":[2,40,93],"study":[3,24],"on":[4,20,70,95],"the":[5,12,57,65,97,109],"contributions":[6],"to":[7,54,88],"Diarization":[8],"Error":[9],"Rate":[10],"by":[11,25,85],"various":[13],"components":[14],"of":[15,42,60,67,103,107],"speaker":[16,68,98],"diarization":[17,63],"system.":[18,82],"Following":[19],"from":[21,100],"an":[22],"earlier":[23],"Huijbregts":[26],"and":[27,34,47],"Wooters,":[28],"we":[29,51],"extend":[30],"into":[31],"more":[32],"areas":[33],"draw":[35],"somewhat":[36],"different":[37],"conclusions.":[38],"From":[39],"series":[41],"experiments":[43],"combining":[44],"real,":[45],"oracle":[46],"ideal":[48],"system":[49],"components,":[50],"are":[52],"able":[53],"conclude":[55,84],"that":[56,74],"primary":[58],"cause":[59],"error":[61],"in":[62,76,79],"is":[64,75,112],"training":[66,96],"models":[69,99],"impure":[71],"data,":[72,110],"something":[73],"fact":[77],"done":[78],"every":[80],"current":[81],"suggesting":[86],"ways":[87],"improve":[89],"future":[90],"systems,":[91],"including":[92],"focus":[94],"smaller":[101],"quantities":[102],"pure":[104],"data":[105],"instead":[106],"all":[108],"as":[111],"currently":[113],"done.":[114]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
