{"id":"https://openalex.org/W1975884129","doi":"https://doi.org/10.1109/mmsp.2012.6343426","title":"Incorporation of the ASR output in speaker segmentation and clustering within the task of speaker diarization of broadcast streams","display_name":"Incorporation of the ASR output in speaker segmentation and clustering within the task of speaker diarization of broadcast streams","publication_year":2012,"publication_date":"2012-09-01","ids":{"openalex":"https://openalex.org/W1975884129","doi":"https://doi.org/10.1109/mmsp.2012.6343426","mag":"1975884129"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp.2012.6343426","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2012.6343426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 14th International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"},"type":"article","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/A5022347882","display_name":"Jan Silovsk\u00fd","orcid":null},"institutions":[{"id":"https://openalex.org/I147009085","display_name":"Technical University of Liberec","ror":"https://ror.org/02jtk7k02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I147009085"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Silovsky","raw_affiliation_strings":["Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Czech Republic","Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Czech Republic#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Czech Republic","institution_ids":["https://openalex.org/I147009085"]},{"raw_affiliation_string":"Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Czech Republic#TAB#","institution_ids":["https://openalex.org/I147009085"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089093629","display_name":"Jind\u0159ich \u017d\u010f\u00e1nsk\u00fd","orcid":null},"institutions":[{"id":"https://openalex.org/I147009085","display_name":"Technical University of Liberec","ror":"https://ror.org/02jtk7k02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I147009085"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jindrich Zdansky","raw_affiliation_strings":["Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Czech Republic","Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Czech Republic#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Czech Republic","institution_ids":["https://openalex.org/I147009085"]},{"raw_affiliation_string":"Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Czech Republic#TAB#","institution_ids":["https://openalex.org/I147009085"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033391650","display_name":"Jan Nouza","orcid":"https://orcid.org/0000-0003-3960-3194"},"institutions":[{"id":"https://openalex.org/I147009085","display_name":"Technical University of Liberec","ror":"https://ror.org/02jtk7k02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I147009085"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Nouza","raw_affiliation_strings":["Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Czech Republic","Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Czech Republic#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Czech Republic","institution_ids":["https://openalex.org/I147009085"]},{"raw_affiliation_string":"Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Czech Republic#TAB#","institution_ids":["https://openalex.org/I147009085"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007129369","display_name":"Petr \u010cerva","orcid":"https://orcid.org/0000-0003-0767-0106"},"institutions":[{"id":"https://openalex.org/I147009085","display_name":"Technical University of Liberec","ror":"https://ror.org/02jtk7k02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I147009085"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Petr Cerva","raw_affiliation_strings":["Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Czech Republic","Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Czech Republic#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Czech Republic","institution_ids":["https://openalex.org/I147009085"]},{"raw_affiliation_string":"Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Czech Republic#TAB#","institution_ids":["https://openalex.org/I147009085"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080421250","display_name":"Jan Pra\u017e\u00e1k","orcid":"https://orcid.org/0000-0002-0784-149X"},"institutions":[{"id":"https://openalex.org/I147009085","display_name":"Technical University of Liberec","ror":"https://ror.org/02jtk7k02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I147009085"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Prazak","raw_affiliation_strings":["Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Czech Republic","Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Czech Republic#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Czech Republic","institution_ids":["https://openalex.org/I147009085"]},{"raw_affiliation_string":"Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Czech Republic#TAB#","institution_ids":["https://openalex.org/I147009085"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7691,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.86036647,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"4625","issue":null,"first_page":"118","last_page":"123"},"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":0.9993000030517578,"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":0.9955000281333923,"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":0.9239648580551147},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.799493670463562},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7338985204696655},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5245383381843567},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.48454800248146057},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4778991937637329},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.473537415266037},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.467443585395813},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4307257831096649},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.42538678646087646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39686572551727295},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3956175148487091},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.27311503887176514}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9239648580551147},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.799493670463562},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7338985204696655},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5245383381843567},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.48454800248146057},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4778991937637329},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.473537415266037},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.467443585395813},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4307257831096649},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.42538678646087646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39686572551727295},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3956175148487091},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27311503887176514},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp.2012.6343426","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2012.6343426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 14th International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6399999856948853,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323199","display_name":"Technick\u00e1 Univerzita v Liberci","ror":"https://ror.org/02jtk7k02"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W83776700","https://openalex.org/W129040001","https://openalex.org/W1482605500","https://openalex.org/W1556857061","https://openalex.org/W2115861008","https://openalex.org/W2121415728","https://openalex.org/W2136752740","https://openalex.org/W2150769028","https://openalex.org/W2159591770","https://openalex.org/W2405472765","https://openalex.org/W2407232104","https://openalex.org/W6605248788","https://openalex.org/W6628911050"],"related_works":["https://openalex.org/W1963976507","https://openalex.org/W2206035908","https://openalex.org/W3119288895","https://openalex.org/W1493012537","https://openalex.org/W2185075503","https://openalex.org/W2162158162","https://openalex.org/W2131673591","https://openalex.org/W4247736853","https://openalex.org/W2104528589","https://openalex.org/W3155728191"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,60,152],"study":[4],"the":[5,13,22,34,41,73,89,106,114,121,128,137,155],"effect":[6],"of":[7,9,33,47,56,68,105,120,143,157],"incorporation":[8],"automatic":[10,49],"transcriptions":[11],"in":[12,72,141],"speaker":[14,85,145],"diarization":[15,23,35,146],"process.":[16],"We":[17,134],"aim":[18],"to":[19,92],"improve":[20],"both":[21,144],"accuracy":[24],"as":[25,81],"evaluated":[26],"by":[27,108],"standard":[28],"objective":[29],"measures":[30],"and":[31,66,88,111,147],"quality":[32],"output":[36,46],"from":[37],"user's":[38],"perspective.":[39],"Although":[40],"presented":[42,122],"approach":[43,123,138],"relies":[44],"on":[45],"an":[48],"speech":[50],"recognizer,":[51],"it":[52],"makes":[53],"no":[54,100],"use":[55,61],"lexical":[57],"information.":[58],"Instead,":[59],"information":[62,78,102],"about":[63],"word":[64],"boundaries":[65],"classification":[67],"non-speech":[69],"events":[70],"occurring":[71],"processed":[74],"stream.":[75],"The":[76,117],"former":[77],"is":[79,167],"used":[80],"constraining":[82],"condition":[83],"for":[84],"change-point":[86],"candidates":[87],"latter":[90],"facilitate":[91],"neglect":[93],"various":[94],"vocal":[95],"noise":[96],"sounds":[97],"that":[98,136,154],"carry":[99],"speaker-specific":[101],"(considering":[103],"representation":[104],"signal":[107],"cepstral":[109],"features)":[110],"thus":[112],"harm":[113],"speaker's":[115],"representation.":[116],"experimental":[118],"evaluation":[119],"was":[124],"carried":[125],"out":[126],"using":[127],"COST278":[129],"multilingual":[130],"broadcast":[131],"news":[132],"database.":[133],"demonstrate":[135],"yields":[139],"improvement":[140],"terms":[142],"segmentation":[148],"performance":[149],"measures.":[150],"Furthermore,":[151],"show":[153],"number":[156],"change-points":[158],"detected":[159],"within":[160],"words":[161],"(and":[162],"not":[163],"at":[164],"their":[165],"boundaries)":[166],"significantly":[168],"reduced.":[169]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
