{"id":"https://openalex.org/W2136745572","doi":"https://doi.org/10.1109/icassp.2012.6288840","title":"Speech overlap detection and attribution using convolutive non-negative sparse coding","display_name":"Speech overlap detection and attribution using convolutive non-negative sparse coding","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2136745572","doi":"https://doi.org/10.1109/icassp.2012.6288840","mag":"2136745572"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288840","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288840","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/node?id=1137899","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069973475","display_name":"Ravichander Vipperla","orcid":null},"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":"Ravichander Vipperla","raw_affiliation_strings":["Multimedia Communications Department, Eurecom Institute, Sophia-Antipolis, France","Multimedia Communications Department, EURECOM, Sophia-Antipolis, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Communications Department, Eurecom Institute, Sophia-Antipolis, France","institution_ids":["https://openalex.org/I1902872"]},{"raw_affiliation_string":"Multimedia Communications Department, EURECOM, Sophia-Antipolis, France","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"middle","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":"Jurgen T. Geiger","raw_affiliation_strings":["Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Germany","Institute for Human-Machine Communication Technische Universitat Munchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Institute for Human-Machine Communication Technische Universitat Munchen, Germany","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/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":"Simon Bozonnet","raw_affiliation_strings":["Multimedia Communications Department, Eurecom Institute, Sophia-Antipolis, France","Multimedia Communications Department, EURECOM, Sophia-Antipolis, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Communications Department, Eurecom Institute, Sophia-Antipolis, France","institution_ids":["https://openalex.org/I1902872"]},{"raw_affiliation_string":"Multimedia Communications Department, EURECOM, Sophia-Antipolis, France","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391562","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0003-4872-4860"},"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":"Dong Wang","raw_affiliation_strings":["Multimedia Communications Department, Eurecom Institute, Sophia-Antipolis, France","Multimedia Communications Department, EURECOM, Sophia-Antipolis, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Communications Department, Eurecom Institute, Sophia-Antipolis, France","institution_ids":["https://openalex.org/I1902872"]},{"raw_affiliation_string":"Multimedia Communications Department, EURECOM, Sophia-Antipolis, France","institution_ids":["https://openalex.org/I1902872"]}]},{"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":["Multimedia Communications Department, Eurecom Institute, Sophia-Antipolis, France","Multimedia Communications Department, EURECOM, Sophia-Antipolis, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Communications Department, Eurecom Institute, Sophia-Antipolis, France","institution_ids":["https://openalex.org/I1902872"]},{"raw_affiliation_string":"Multimedia Communications Department, EURECOM, Sophia-Antipolis, 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":"Bjorn Schuller","raw_affiliation_strings":["Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Germany","Institute for Human-Machine Communication Technische Universitat Munchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Institute for Human-Machine Communication Technische Universitat Munchen, 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":["Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Germany","Institute for Human-Machine Communication Technische Universitat Munchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Institute for Human-Machine Communication Technische Universitat Munchen, 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":false,"cited_by_count":31,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4181","last_page":"4184"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9991000294685364,"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":0.9980999827384949,"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/computer-science","display_name":"Computer science","score":0.6588156819343567},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.596619725227356},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4929790496826172},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.461805522441864},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42326968908309937},{"id":"https://openalex.org/keywords/neural-coding","display_name":"Neural coding","score":0.42252209782600403},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20213773846626282},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1042712926864624}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6588156819343567},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.596619725227356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4929790496826172},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.461805522441864},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42326968908309937},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.42252209782600403},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20213773846626282},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1042712926864624}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2012.6288840","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288840","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:fr.eurecom:3595","is_oa":false,"landing_page_url":"http://www.eurecom.fr/publication/3595","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":"ICASSP 2012, 37th International Conference on Acoustics, Speech and Signal Processing, March 25-30, 2012, Kyoto, Japan","raw_type":"Conference"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1137899","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1137899","pdf_url":null,"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"}],"best_oa_location":{"id":"pmh:oai:mediatum.ub.tum.de:node/1137899","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1137899","pdf_url":null,"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W196703252","https://openalex.org/W1902027874","https://openalex.org/W2081074144","https://openalex.org/W2097583714","https://openalex.org/W2106103082","https://openalex.org/W2109097134","https://openalex.org/W2115130489","https://openalex.org/W2124149378","https://openalex.org/W2135029798","https://openalex.org/W2406713305","https://openalex.org/W2545232173","https://openalex.org/W6607949085","https://openalex.org/W6675718704","https://openalex.org/W6676496947","https://openalex.org/W6680012447","https://openalex.org/W6713701993"],"related_works":["https://openalex.org/W2132101312","https://openalex.org/W2078080292","https://openalex.org/W2111634407","https://openalex.org/W2949777679","https://openalex.org/W1546922341","https://openalex.org/W2772917594","https://openalex.org/W4306742369","https://openalex.org/W2033914206","https://openalex.org/W2042327336","https://openalex.org/W2065031478"],"abstract_inverted_index":{"Overlapping":[0],"speech":[1,25],"is":[2,68,109],"known":[3],"to":[4,31,51,57,72,91,111],"degrade":[5],"speaker":[6,12,107,114],"diarization":[7,103],"performance":[8],"with":[9],"impacts":[10],"on":[11,79],"clustering":[13],"and":[14,27,67,75],"segmentation.":[15],"While":[16],"previous":[17],"work":[18],"made":[19],"important":[20],"advances":[21],"in":[22,28,120],"detecting":[23],"overlapping":[24,121],"intervals":[26],"attributing":[29],"them":[30],"relevant":[32],"speakers,":[33],"the":[34,42,52,85,113],"problem":[35],"remains":[36],"largely":[37],"unsolved.":[38],"This":[39],"paper":[40],"reports":[41],"first":[43],"application":[44],"of":[45],"convolutive":[46],"non-negative":[47],"sparse":[48],"coding":[49],"(CNSC)":[50],"overlap":[53,73,98],"problem.":[54],"CNSC":[55,86,105],"aims":[56],"decompose":[58],"a":[59,92,101],"composite":[60],"signal":[61],"into":[62],"its":[63],"underlying":[64],"contributory":[65],"parts":[66],"thus":[69],"naturally":[70],"suited":[71],"detection":[74],"attribution.":[76],"Experimental":[77],"results":[78,90],"NIST":[80],"RT":[81],"data":[82],"show":[83],"that":[84],"approach":[87],"gives":[88],"comparable":[89],"state-of-the-art":[93],"hidden":[94],"Markov":[95],"model":[96],"based":[97,106],"detector.":[99],"In":[100],"practical":[102],"system,":[104],"attribution":[108],"shown":[110],"reduce":[112],"error":[115],"by":[116],"over":[117],"40%":[118],"relative":[119],"segments.":[122]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
