{"id":"https://openalex.org/W1606894530","doi":"https://doi.org/10.1109/icassp.2015.7178881","title":"Diarization resegmentation in the factor analysis subspace","display_name":"Diarization resegmentation in the factor analysis subspace","alternate_titles":[],"publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1606894530","doi":"https://doi.org/10.1109/icassp.2015.7178881","mag":"1606894530"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178881","doi":"https://doi.org/10.1109/icassp.2015.7178881","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178881","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W1606894530"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"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/A5046596198","display_name":"Gregory Sell","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gregory Sell","raw_affiliation_strings":["Human Language Technology Center of Excellence Johns Hopkins University, Baltimore, MD, USA","Human Language Technol. Center of Excellence Johns, Hopkins Univ., Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Center of Excellence Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Human Language Technol. Center of Excellence Johns, Hopkins Univ., Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000143881","display_name":"Daniel Garcia-Romero","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Garcia-Romero","raw_affiliation_strings":["Human Language Technology Center of Excellence Johns Hopkins University, Baltimore, MD, USA","Human Language Technol. Center of Excellence Johns, Hopkins Univ., Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Center of Excellence Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Human Language Technol. Center of Excellence Johns, Hopkins Univ., Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.8718,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.72088881,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4794","last_page":"4798"},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9878000020980835,"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":0.9878000020980835,"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":0.008799999952316284,"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/T12031","display_name":"Speech and dialogue systems","score":0.0013000000035390258,"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-diarization","display_name":"speaker diarization","score":0.8610000014305115},{"id":"https://openalex.org/keywords/resegmentation","display_name":"resegmentation","score":0.9240000247955322},{"id":"https://openalex.org/keywords/segment-clustering","display_name":"segment clustering","score":0.699999988079071},{"id":"https://openalex.org/keywords/speaker-clustering","display_name":"speaker clustering","score":0.7279999852180481},{"id":"https://openalex.org/keywords/mel-frequency-cepstral-coefficients","display_name":"Mel-frequency cepstral coefficients","score":0.9350000023841858},{"id":"https://openalex.org/keywords/callhome-corpus","display_name":"CallHome corpus","score":0.8840000033378601},{"id":"https://openalex.org/keywords/conversational-telephone-speech","display_name":"conversational telephone speech","score":0.9300000071525574}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8766072392463684},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7777270078659058},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.7303236722946167},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6761671304702759},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.674045205116272},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.591515839099884},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5680536031723022},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5058391094207764},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.4943816661834717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4907025098800659},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4660922586917877},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.44255438446998596},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.38432008028030396},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3537813425064087},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.22976398468017578},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7178881","doi":"https://doi.org/10.1109/icassp.2015.7178881","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178881","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322748","display_name":"Vysok\u00e9 U\u010den\u00ed Technick\u00e9 v Brn\u011b","ror":"https://ror.org/03613d656"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W118310762","https://openalex.org/W1965819578","https://openalex.org/W2038101708","https://openalex.org/W2093499222","https://openalex.org/W2115599677","https://openalex.org/W2125642021","https://openalex.org/W2289985966","https://openalex.org/W2400584454","https://openalex.org/W4285719527","https://openalex.org/W6604723554"],"related_works":["https://openalex.org/W1502693945","https://openalex.org/W2038101708","https://openalex.org/W2616479044","https://openalex.org/W2405802804","https://openalex.org/W2401936336","https://openalex.org/W1998280908","https://openalex.org/W2188521373","https://openalex.org/W7098662709","https://openalex.org/W2115599677","https://openalex.org/W2001936727"],"abstract_inverted_index":{"Resegmentation":[0],"is":[1],"an":[2,20,43],"important":[3],"post-processing":[4],"step":[5],"to":[6],"refine":[7],"the":[8,72],"rough":[9],"boundaries":[10],"of":[11,19,69],"diarization":[12,66],"systems":[13],"that":[14,47],"rely":[15],"on":[16,71],"segment":[17],"clustering":[18,61],"initial":[21],"uniform":[22],"segmentation.":[23],"Past":[24],"work":[25],"has":[26],"primarily":[27],"used":[28],"a":[29,59,65],"Viterbi":[30],"resegmentation":[31,46],"with":[32,58],"MFCC":[33],"features":[34],"for":[35,45],"this":[36,39,56],"purpose.":[37],"In":[38],"paper,":[40],"we":[41,63],"examine":[42],"algorithm":[44],"operates":[48],"instead":[49],"in":[50],"factor":[51],"analysis":[52],"subspace.":[53],"By":[54],"combining":[55],"system":[57],"speaker":[60],"front-end,":[62],"yield":[64],"error":[67],"rate":[68],"11.5%":[70],"CALLHOME":[73],"conversational":[74],"telephone":[75],"speech":[76],"corpus.":[77]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W1606894530","counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-11-16T12:05:36.265796","created_date":"2016-06-24T00:00:00"}
