{"id":"https://openalex.org/W2059891707","doi":"https://doi.org/10.1109/icumt.2009.5345325","title":"Speech activity and speaker novelty detection methods for meeting processing","display_name":"Speech activity and speaker novelty detection methods for meeting processing","publication_year":2009,"publication_date":"2009-10-01","ids":{"openalex":"https://openalex.org/W2059891707","doi":"https://doi.org/10.1109/icumt.2009.5345325","mag":"2059891707"},"language":"en","primary_location":{"id":"doi:10.1109/icumt.2009.5345325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icumt.2009.5345325","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 International Conference on Ultra Modern Telecommunications &amp; Workshops","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/A5103479846","display_name":"Masahide Sugiyama","orcid":null},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Masahide Sugiyama","raw_affiliation_strings":["Human Interface Laboratory, University of Aizu, Fukushima, Japan","Human Interface Lab, The University of Aizu, Fukushima, Japan"],"affiliations":[{"raw_affiliation_string":"Human Interface Laboratory, University of Aizu, Fukushima, Japan","institution_ids":["https://openalex.org/I141591182"]},{"raw_affiliation_string":"Human Interface Lab, The University of Aizu, Fukushima, Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039443541","display_name":"Konstantin Markov","orcid":"https://orcid.org/0000-0003-1838-4789"},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Konstantin Markov","raw_affiliation_strings":["Human Interface Laboratory, University of Aizu, Fukushima, Japan","Human Interface Lab, The University of Aizu, Fukushima, Japan"],"affiliations":[{"raw_affiliation_string":"Human Interface Laboratory, University of Aizu, Fukushima, Japan","institution_ids":["https://openalex.org/I141591182"]},{"raw_affiliation_string":"Human Interface Lab, The University of Aizu, Fukushima, Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007008031","display_name":"Andrey Ronzhin","orcid":"https://orcid.org/0000-0002-8903-3508"},"institutions":[{"id":"https://openalex.org/I4210103826","display_name":"St. Petersburg Institute for Informatics and Automation","ror":"https://ror.org/01ccb9w37","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210097085","https://openalex.org/I4210103826"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Andrey Ronzhin","raw_affiliation_strings":["Speech and Multimodal Interfaces Laboratory, Saint Petersburg Institute of Informatics and Automation, Russian Academy of Sciences, Saint Petersburg, Russia","Speech and Multimodal Interfaces Laboratory, St. Petersburg Institute for Informatics and Automation, Russia"],"affiliations":[{"raw_affiliation_string":"Speech and Multimodal Interfaces Laboratory, Saint Petersburg Institute of Informatics and Automation, Russian Academy of Sciences, Saint Petersburg, Russia","institution_ids":["https://openalex.org/I4210103826"]},{"raw_affiliation_string":"Speech and Multimodal Interfaces Laboratory, St. Petersburg Institute for Informatics and Automation, Russia","institution_ids":["https://openalex.org/I4210103826"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067985539","display_name":"Victor Budkov","orcid":"https://orcid.org/0000-0003-4795-4998"},"institutions":[{"id":"https://openalex.org/I4210103826","display_name":"St. Petersburg Institute for Informatics and Automation","ror":"https://ror.org/01ccb9w37","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210097085","https://openalex.org/I4210103826"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Victor Budkov","raw_affiliation_strings":["Speech and Multimodal Interfaces Laboratory, Saint Petersburg Institute of Informatics and Automation, Russian Academy of Sciences, Saint Petersburg, Russia","Speech and Multimodal Interfaces Laboratory, St. Petersburg Institute for Informatics and Automation, Russia"],"affiliations":[{"raw_affiliation_string":"Speech and Multimodal Interfaces Laboratory, Saint Petersburg Institute of Informatics and Automation, Russian Academy of Sciences, Saint Petersburg, Russia","institution_ids":["https://openalex.org/I4210103826"]},{"raw_affiliation_string":"Speech and Multimodal Interfaces Laboratory, St. Petersburg Institute for Informatics and Automation, Russia","institution_ids":["https://openalex.org/I4210103826"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032870944","display_name":"Alexey Karpov","orcid":"https://orcid.org/0000-0003-3424-652X"},"institutions":[{"id":"https://openalex.org/I4210103826","display_name":"St. Petersburg Institute for Informatics and Automation","ror":"https://ror.org/01ccb9w37","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210097085","https://openalex.org/I4210103826"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Alexey Karpov","raw_affiliation_strings":["Speech and Multimodal Interfaces Laboratory, Saint Petersburg Institute of Informatics and Automation, Russian Academy of Sciences, Saint Petersburg, Russia","Speech and Multimodal Interfaces Laboratory, St. Petersburg Institute for Informatics and Automation, Russia"],"affiliations":[{"raw_affiliation_string":"Speech and Multimodal Interfaces Laboratory, Saint Petersburg Institute of Informatics and Automation, Russian Academy of Sciences, Saint Petersburg, Russia","institution_ids":["https://openalex.org/I4210103826"]},{"raw_affiliation_string":"Speech and Multimodal Interfaces Laboratory, St. Petersburg Institute for Informatics and Automation, Russia","institution_ids":["https://openalex.org/I4210103826"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111440667","display_name":"Maria Prischepa","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103826","display_name":"St. Petersburg Institute for Informatics and Automation","ror":"https://ror.org/01ccb9w37","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210097085","https://openalex.org/I4210103826"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Maria Prischepa","raw_affiliation_strings":["Speech and Multimodal Interfaces Laboratory, Saint Petersburg Institute of Informatics and Automation, Russian Academy of Sciences, Saint Petersburg, Russia","Speech and Multimodal Interfaces Laboratory, St. Petersburg Institute for Informatics and Automation, Russia"],"affiliations":[{"raw_affiliation_string":"Speech and Multimodal Interfaces Laboratory, Saint Petersburg Institute of Informatics and Automation, Russian Academy of Sciences, Saint Petersburg, Russia","institution_ids":["https://openalex.org/I4210103826"]},{"raw_affiliation_string":"Speech and Multimodal Interfaces Laboratory, St. Petersburg Institute for Informatics and Automation, Russia","institution_ids":["https://openalex.org/I4210103826"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103479846"],"corresponding_institution_ids":["https://openalex.org/I141591182"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10222851,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9994000196456909,"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":0.9987000226974487,"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":0.8631995916366577},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8064956665039062},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.7909995913505554},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7882927060127258},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.703694224357605},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5794801115989685},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5545364022254944},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5035378336906433},{"id":"https://openalex.org/keywords/novelty-detection","display_name":"Novelty detection","score":0.4986131191253662},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.47704023122787476},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2748952805995941}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8631995916366577},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8064956665039062},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.7909995913505554},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7882927060127258},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.703694224357605},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5794801115989685},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5545364022254944},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5035378336906433},{"id":"https://openalex.org/C2778924833","wikidata":"https://www.wikidata.org/wiki/Q7064603","display_name":"Novelty detection","level":3,"score":0.4986131191253662},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.47704023122787476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2748952805995941},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icumt.2009.5345325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icumt.2009.5345325","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 International Conference on Ultra Modern Telecommunications &amp; Workshops","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1016.7007","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1016.7007","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/Konstantin_Markov/publication/221003698_Speech_activity_and_speaker_novelty_detection_methods_for_meeting_processing/links/0046352afb34c12b0f000000.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1030.9456","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1030.9456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/Konstantin_Markov/publication/221003698_Speech_activity_and_speaker_novelty_detection_methods_for_meeting_processing/links/0deec5282f4842c000000000.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W21371201","https://openalex.org/W38131637","https://openalex.org/W76901566","https://openalex.org/W191300215","https://openalex.org/W196703252","https://openalex.org/W1946893126","https://openalex.org/W2041823554","https://openalex.org/W2104804886","https://openalex.org/W2104835909","https://openalex.org/W2149220986","https://openalex.org/W2157775762","https://openalex.org/W2159591770","https://openalex.org/W6600930061"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"Segmentation":[0],"of":[1,15,21,53,56,61,79,84],"multi-speaker":[2],"meeting":[3,69],"audio":[4],"data":[5],"recorded":[6],"with":[7],"several":[8],"microphones":[9,57],"into":[10],"speech/silence":[11],"frames":[12],"is":[13,75],"one":[14],"the":[16,22,39,62,67,80,85],"first":[17],"tasks":[18],"at":[19],"development":[20],"speaker":[23,87],"diarization":[24,88],"system.":[25,89],"Energy":[26],"normalization":[27],"techniques":[28],"and":[29,58],"signal":[30],"correlation":[31],"methods":[32],"are":[33,71],"used":[34],"in":[35,42],"order":[36],"to":[37,77],"avoid":[38],"crosstalk":[40],"problem,":[41],"which":[43],"participant's":[44],"speech":[45],"appears":[46],"on":[47],"other":[48],"participants'":[49],"microphones.":[50],"A":[51],"comparison":[52],"different":[54],"types":[55],"a":[59],"configuration":[60],"recording":[63],"devices":[64],"implemented":[65],"inside":[66],"intelligent":[68],"room":[70],"described.":[72],"Special":[73],"attention":[74],"paid":[76],"improvement":[78],"novelty":[81],"detection":[82],"performance":[83],"on-line":[86]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
