{"id":"https://openalex.org/W2073495057","doi":"https://doi.org/10.1109/tasl.2012.2215588","title":"Wordless Sounds: Robust Speaker Diarization Using Privacy-Preserving Audio Representations","display_name":"Wordless Sounds: Robust Speaker Diarization Using Privacy-Preserving Audio Representations","publication_year":2012,"publication_date":"2012-08-27","ids":{"openalex":"https://openalex.org/W2073495057","doi":"https://doi.org/10.1109/tasl.2012.2215588","mag":"2073495057"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2012.2215588","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2215588","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/184043","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080341961","display_name":"Sree Hari Krishnan Parthasarathi","orcid":null},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sree Hari Krishnan Parthasarathi","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108291827","display_name":"H. Bourlard","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"H. Bourlard","raw_affiliation_strings":["Ecole Polytechnique F\u00e9d\u00e9rale, Lausanne (EPFL), Martigny, Switzerland","Idiap Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique F\u00e9d\u00e9rale, Lausanne (EPFL), Martigny, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012965551","display_name":"Daniel G\u00e1tica-P\u00e9rez","orcid":"https://orcid.org/0000-0001-5488-2182"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"D. Gatica-Perez","raw_affiliation_strings":["Ecole Polytechnique F\u00e9d\u00e9rale, Lausanne (EPFL), Martigny, Switzerland","Idiap Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique F\u00e9d\u00e9rale, Lausanne (EPFL), Martigny, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4621,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.8543777,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"21","issue":"1","first_page":"85","last_page":"98"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8348680734634399},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.8348203897476196},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7990423440933228},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7689804434776306},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7478749752044678},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6399452686309814},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.572035551071167},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.48896610736846924},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.48324093222618103},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.47271057963371277},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4530288279056549},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44295746088027954},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3714616894721985},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3416889011859894}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8348680734634399},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8348203897476196},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7990423440933228},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7689804434776306},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7478749752044678},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6399452686309814},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.572035551071167},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48896610736846924},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.48324093222618103},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.47271057963371277},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4530288279056549},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44295746088027954},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3714616894721985},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3416889011859894},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":8,"locations":[{"id":"doi:10.1109/tasl.2012.2215588","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2215588","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.649.8053","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.649.8053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://publications.idiap.ch/downloads/papers/2012/Parthasarathi_TASLP_2012.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.650.9840","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.650.9840","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://publications.idiap.ch/downloads/reports/2011/Parthasarathi_Idiap-RR-28-2012.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:184043","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/184043","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.epfl.ch:192572","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/192572","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.epfl.ch:192757","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/192757","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.tind.io:192572","is_oa":true,"landing_page_url":"http://publications.idiap.ch/index.php/publications/showcite/Parthasarathi_Idiap-RR-28-2012","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"research article"},{"id":"pmh:oai:infoscience.tind.io:192757","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/98591","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"report"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:184043","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/184043","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W11987703","https://openalex.org/W62987774","https://openalex.org/W811578723","https://openalex.org/W1482605500","https://openalex.org/W1490216641","https://openalex.org/W1495076553","https://openalex.org/W1553004968","https://openalex.org/W1572989473","https://openalex.org/W1590057516","https://openalex.org/W1787748203","https://openalex.org/W1966264494","https://openalex.org/W1999405202","https://openalex.org/W2012897754","https://openalex.org/W2053966553","https://openalex.org/W2056411660","https://openalex.org/W2059182962","https://openalex.org/W2074263569","https://openalex.org/W2077611854","https://openalex.org/W2084609288","https://openalex.org/W2088562567","https://openalex.org/W2095635231","https://openalex.org/W2099111195","https://openalex.org/W2100495367","https://openalex.org/W2106883183","https://openalex.org/W2108950108","https://openalex.org/W2110798204","https://openalex.org/W2112164460","https://openalex.org/W2140766383","https://openalex.org/W2140833774","https://openalex.org/W2148882869","https://openalex.org/W2150008717","https://openalex.org/W2156255174","https://openalex.org/W2157867825","https://openalex.org/W2159948109","https://openalex.org/W2165712214","https://openalex.org/W2170166043","https://openalex.org/W2171757151","https://openalex.org/W2187722256","https://openalex.org/W2338994564","https://openalex.org/W2736230390","https://openalex.org/W4285719527","https://openalex.org/W6600510284","https://openalex.org/W6628911050","https://openalex.org/W6629128663","https://openalex.org/W6629558825","https://openalex.org/W6635201662","https://openalex.org/W6659344013","https://openalex.org/W6676481782","https://openalex.org/W6680789778","https://openalex.org/W6680887930","https://openalex.org/W6740917271"],"related_works":["https://openalex.org/W1963976507","https://openalex.org/W2206035908","https://openalex.org/W3119288895","https://openalex.org/W1977167953","https://openalex.org/W2185075503","https://openalex.org/W2162158162","https://openalex.org/W2749720872","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"robust":[3],"privacy-sensitive":[4,87,162],"audio":[5,17,88,163],"features":[6,18,102,129,164],"for":[7,23,85,103],"speaker":[8,24,104],"diarization":[9,25,105,123],"in":[10,26,106,143],"multiparty":[11],"conversations:":[12],"i.e.,":[13],"a":[14,27,78],"set":[15],"of":[16,48,50,60,141,145],"having":[19],"low":[20],"linguistic":[21,146],"information":[22,65],"single":[28,132],"and":[29,46,72,151],"multiple":[30],"distant":[31,133],"microphone":[32,109,134],"scenarios.":[33,110],"We":[34,90],"systematically":[35],"investigate":[36],"Linear":[37],"Prediction":[38],"(LP)":[39],"residual.":[40],"Issues":[41],"such":[42],"as":[43],"prediction":[44],"order":[45],"choice":[47],"representation":[49],"LP":[51,61],"residual":[52,62],"are":[53],"studied.":[54],"Additionally,":[55],"we":[56,76,148],"explore":[57],"the":[58,95,108,113,119,127,131,139,158],"combination":[59],"with":[63],"subband":[64],"from":[66],"2.5":[67],"kHz":[68,71],"to":[69,126,161,171],"3.5":[70],"spectral":[73],"slope.":[74],"Next,":[75],"propose":[77],"supervised":[79],"framework":[80],"using":[81],"deep":[82],"neural":[83],"architecture":[84],"deriving":[86],"features.":[89,173],"benchmark":[91],"these":[92],"approaches":[93,121,160],"against":[94],"traditional":[96],"Mel":[97],"Frequency":[98],"Cepstral":[99],"Coefficients":[100],"(MFCC)":[101],"both":[107],"Experiments":[111],"on":[112,130],"RT07":[114],"evaluation":[115],"dataset":[116],"show":[117],"that":[118,157],"proposed":[120,159],"yield":[122,165],"performance":[124],"close":[125],"MFCC":[128,172],"dataset.":[135],"To":[136],"objectively":[137],"evaluate":[138],"notion":[140],"privacy":[142],"terms":[144],"information,":[147],"perform":[149],"human":[150],"automatic":[152],"speech":[153],"recognition":[154,168],"tests,":[155],"showing":[156],"much":[166],"lower":[167],"accuracies":[169],"compared":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}