{"id":"https://openalex.org/W2400584454","doi":"https://doi.org/10.21437/interspeech.2012-163","title":"On the use of spectral and iterative methods for speaker diarization","display_name":"On the use of spectral and iterative methods for speaker diarization","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W2400584454","doi":"https://doi.org/10.21437/interspeech.2012-163","mag":"2400584454"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-163","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-163","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","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/A5051278718","display_name":"Stephen Shum","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stephen Shum","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["Massachusetts Institute Of Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"482","last_page":"485"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9958999752998352,"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":0.991100013256073,"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":0.7332584857940674},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7003308534622192},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5614989399909973},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.44514837861061096}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7332584857940674},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7003308534622192},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5614989399909973},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.44514837861061096}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2012-163","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-163","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.258.7552","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.258.7552","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.sls.lcs.mit.edu/sls/publications/2012/Shum-Interspeech12.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.708.2496","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.708.2496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://people.csail.mit.edu/sshum/papers/interspeech2012_sshum.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W36432376","https://openalex.org/W48568691","https://openalex.org/W2041823554","https://openalex.org/W2115599677","https://openalex.org/W2125642021","https://openalex.org/W2135537007","https://openalex.org/W2145001205","https://openalex.org/W2150769028","https://openalex.org/W2165874743","https://openalex.org/W2289985966","https://openalex.org/W2610299321"],"related_works":["https://openalex.org/W2162158162","https://openalex.org/W1521049138","https://openalex.org/W1509309911","https://openalex.org/W2144208207","https://openalex.org/W2175373321","https://openalex.org/W2499802997","https://openalex.org/W1497807607","https://openalex.org/W1813780412","https://openalex.org/W2128773298","https://openalex.org/W2160753975"],"abstract_inverted_index":{"This":[0],"paper":[1],"extends":[2],"upon":[3],"our":[4,23],"previous":[5,24],"work":[6],"using":[7,26],"i-vectors":[8],"for":[9],"speaker":[10],"diarization.":[11],"We":[12],"examine":[13],"the":[14,36,78],"effectiveness":[15],"of":[16,38,72],"spectral":[17],"clustering":[18,28],"as":[19],"an":[20,43,61],"alternative":[21],"to":[22,34,52,70],"approach":[25],"K-means":[27],"and":[29,47,57],"adapt":[30],"a":[31,73],"previously-used":[32],"heuristic":[33],"es-timate":[35],"number":[37],"speakers.":[39],"Additionally,":[40],"we":[41],"consider":[42],"iterative":[44],"optimization":[45],"scheme":[46],"experiment":[48],"with":[49],"its":[50],"ability":[51],"improve":[53],"both":[54],"cluster":[55],"assignments":[56],"segmentation":[58],"boundaries":[59],"in":[60],"unsupervised":[62],"manner.":[63],"Our":[64],"proposed":[65],"methods":[66],"attain":[67],"re-sults":[68],"similar":[69],"those":[71],"state-of-the-art":[74],"benchmark":[75],"set":[76],"on":[77],"multi-speaker":[79],"CallHome":[80],"telephone":[81],"corpus.":[82]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
