{"id":"https://openalex.org/W1922095073","doi":"https://doi.org/10.21437/interspeech.2012-575","title":"Convolutive non-negative sparse coding and new features for speech overlap handling in speaker diarization","display_name":"Convolutive non-negative sparse coding and new features for speech overlap handling in speaker diarization","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W1922095073","doi":"https://doi.org/10.21437/interspeech.2012-575","mag":"1922095073"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-575","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-575","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":true,"oa_status":"green","oa_url":"http://mediatum.ub.tum.de/doc/1137849/document.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030512300","display_name":"J\u00fcrgen T. Geiger","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"J\u00fcrgen T. Geiger","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069973475","display_name":"Ravichander Vipperla","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ravichander Vipperla","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010332658","display_name":"Simon Bozonnet","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Simon Bozonnet","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066811192","display_name":"Nicholas Evans","orcid":"https://orcid.org/0000-0002-8459-1041"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicholas Evans","raw_affiliation_strings":["EURECOM, Valbonne, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EURECOM, Valbonne, France","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn Schuller","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039092855","display_name":"Gerhard Rigoll","orcid":"https://orcid.org/0000-0003-1096-1596"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerhard Rigoll","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2154","last_page":"2157"},"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":0.9991999864578247,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.831380307674408},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7643677592277527},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7191429138183594},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5155734419822693},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4732528328895569},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.46354007720947266},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.44146159291267395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4264291226863861},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39906811714172363},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12008744478225708},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06306818127632141}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.831380307674408},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7643677592277527},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7191429138183594},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5155734419822693},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4732528328895569},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.46354007720947266},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.44146159291267395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4264291226863861},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39906811714172363},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12008744478225708},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06306818127632141}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2012-575","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-575","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:mediatum.ub.tum.de:node/1137849","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1137849","pdf_url":"http://mediatum.ub.tum.de/doc/1137849/document.pdf","source":{"id":"https://openalex.org/S4306400453","display_name":"mediaTUM \u2013 the media and publications repository of the Technical University Munich (Technical University Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},{"id":"pmh:oai:fr.eurecom:3733","is_oa":false,"landing_page_url":"http://www.eurecom.fr/publication/3733","pdf_url":null,"source":{"id":"https://openalex.org/S4377196942","display_name":"Graduate School and Research Center in Digital Science (EURECOM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1902872","host_organization_name":"EURECOM","host_organization_lineage":["https://openalex.org/I1902872"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"INTERSPEECH 2012, 13th Annual Conference of the International Speech Communication Association, Volume3, September 9-13, Portland, Oregon, USA","raw_type":"Conference"}],"best_oa_location":{"id":"pmh:oai:mediatum.ub.tum.de:node/1137849","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1137849","pdf_url":"http://mediatum.ub.tum.de/doc/1137849/document.pdf","source":{"id":"https://openalex.org/S4306400453","display_name":"mediaTUM \u2013 the media and publications repository of the Technical University Munich (Technical University Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.800000011920929,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1922095073.pdf","grobid_xml":"https://content.openalex.org/works/W1922095073.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W168261181","https://openalex.org/W191366985","https://openalex.org/W1481873330","https://openalex.org/W2085662862","https://openalex.org/W2106103082","https://openalex.org/W2109097134","https://openalex.org/W2115130489","https://openalex.org/W2118718620","https://openalex.org/W2124149378","https://openalex.org/W2130162821","https://openalex.org/W2136745572","https://openalex.org/W2151572725","https://openalex.org/W2169264834","https://openalex.org/W2327970305","https://openalex.org/W2406713305","https://openalex.org/W2756372767"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W4245698648","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2405257913"],"abstract_inverted_index":{"The":[0],"effective":[1],"handling":[2],"of":[3,10,14,31,64,73],"overlapping":[4],"speech":[5,87],"is":[6,100],"at":[7],"the":[8,11,15,29,62,74,79,95],"limits":[9],"current":[12],"state":[13],"art":[16],"in":[17,25,85],"speaker":[18,89],"diarization.This":[19],"paper":[20],"presents":[21],"our":[22,57],"latest":[23],"work":[24],"overlap":[26,65,68,91],"detection.We":[27],"report":[28],"combination":[30],"features":[32,45],"derived":[33],"through":[34,61],"convolutive":[35],"nonnegative":[36],"sparse":[37],"coding":[38],"and":[39,43,67,88,93],"new":[40,80],"energy,":[41],"spectral":[42],"voicingrelated":[44],"within":[46],"a":[47,71],"conventional":[48],"HMM":[49],"system.Overlap":[50],"detection":[51],"results":[52],"are":[53],"fully":[54],"integrated":[55],"into":[56],"top-down":[58],"diarization":[59,97],"system":[60,81],"application":[63],"exclusion":[66,92],"labeling.Experiments":[69],"on":[70],"subset":[72],"AMI":[75],"corpus":[76],"show":[77],"that":[78],"delivers":[82],"significant":[83],"reductions":[84],"missed":[86],"error.Through":[90],"labelling":[94],"overall":[96],"error":[98],"rate":[99],"shown":[101],"to":[102],"improve":[103],"by":[104],"6.4":[105],"%":[106],"relative.":[107]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
