{"id":"https://openalex.org/W2160584856","doi":"https://doi.org/10.1109/icassp.2011.5946764","title":"Combining monaural source separation with Long Short-Term Memory for increased robustness in vocalist gender recognition","display_name":"Combining monaural source separation with Long Short-Term Memory for increased robustness in vocalist gender recognition","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2160584856","doi":"https://doi.org/10.1109/icassp.2011.5946764","mag":"2160584856"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5946764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5016747567","display_name":"Felix Weninger","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":"Felix Weninger","raw_affiliation_strings":["Institute of Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munchen, Germany","TUM - Technische Universit\u00e4t Munchen - Technical University Munich - Universit\u00e9 Technique de Munich (Arcisstrasse 21, D- 80333 M\u00fcnchen - Germany)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"TUM - Technische Universit\u00e4t Munchen - Technical University Munich - Universit\u00e9 Technique de Munich (Arcisstrasse 21, D- 80333 M\u00fcnchen - Germany)","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080804613","display_name":"Jean-Louis Durrieu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]},{"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"]}],"countries":["CH","FR"],"is_corresponding":false,"raw_author_name":"Jean-Louis Durrieu","raw_affiliation_strings":["Signal Processing Laboratory, Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","LTCI - Laboratoire Traitement et Communication de l'Information (46 rue Barrault F-75634 Paris Cedex 13 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal Processing Laboratory, Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"LTCI - Laboratoire Traitement et Communication de l'Information (46 rue Barrault F-75634 Paris Cedex 13 - France)","institution_ids":["https://openalex.org/I4210165912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023264395","display_name":"Florian Eyben","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":"Florian Eyben","raw_affiliation_strings":["Institute of Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munchen, Germany","Associate Institute for Signal Processing [Munich] (Technische Universit\u00e4t M\u00fcnchen Arcisstrasse 21 80333 M\u00fcnchen Germany - Germany)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Associate Institute for Signal Processing [Munich] (Technische Universit\u00e4t M\u00fcnchen Arcisstrasse 21 80333 M\u00fcnchen Germany - Germany)","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055423112","display_name":"Ga\u00ebl Richard","orcid":"https://orcid.org/0000-0002-4960-0010"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I205703379","display_name":"Institut Mines-T\u00e9l\u00e9com","ror":"https://ror.org/025vp2923","country_code":"FR","type":"facility","lineage":["https://openalex.org/I205703379"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gael Richard","raw_affiliation_strings":["Institut T\u00e9l\u00e9com, LTCI-CNRS, T\u00e9l\u00e9com Paris Technology, Paris, France","S2A - Signal, Statistique et Apprentissage (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 Palaiseau - France)","IDS - D\u00e9partement Images, Donn\u00e9es, Signal (46, rue Barrault 75013 Paris ; 15 Place Marguerite Perey 91120 Palaiseau (depuis oct 2019) - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut T\u00e9l\u00e9com, LTCI-CNRS, T\u00e9l\u00e9com Paris Technology, Paris, France","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I1294671590","https://openalex.org/I205703379","https://openalex.org/I4210165912"]},{"raw_affiliation_string":"S2A - Signal, Statistique et Apprentissage (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 Palaiseau - France)","institution_ids":["https://openalex.org/I12356871"]},{"raw_affiliation_string":"IDS - D\u00e9partement Images, Donn\u00e9es, Signal (46, rue Barrault 75013 Paris ; 15 Place Marguerite Perey 91120 Palaiseau (depuis oct 2019) - France)","institution_ids":[]}]},{"author_position":"last","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/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]},{"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","GB"],"is_corresponding":false,"raw_author_name":"Bjorn Schuller","raw_affiliation_strings":["Institute of Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munchen, Germany","Imperial College London (South Kensington Campus, London SW7 2AZ - United Kingdom)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Munchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Imperial College London (South Kensington Campus, London SW7 2AZ - United Kingdom)","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2009","issue":null,"first_page":"2196","last_page":"2199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9943000078201294,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.7800809144973755},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7562923431396484},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7203060388565063},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.6453216075897217},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.6073882579803467},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5887046456336975},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5564318299293518},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5385658740997314},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46454906463623047},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.45127880573272705},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4206646680831909},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3963620364665985},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.35194486379623413},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.25086766481399536}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.7800809144973755},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7562923431396484},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7203060388565063},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.6453216075897217},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.6073882579803467},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5887046456336975},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5564318299293518},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5385658740997314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46454906463623047},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45127880573272705},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4206646680831909},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3963620364665985},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35194486379623413},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.25086766481399536},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2011.5946764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.364.4819","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.364.4819","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mmk.ei.tum.de/publ/pdf/11/11wen4.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-02714095v1","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-02714095","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2011 - 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2011, Prague, France. pp.2196-2199, ⟨10.1109/ICASSP.2011.5946764⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:71510","is_oa":false,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/71510","pdf_url":null,"source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W24721013","https://openalex.org/W209492218","https://openalex.org/W1508756421","https://openalex.org/W2057745663","https://openalex.org/W2085662862","https://openalex.org/W2103031592","https://openalex.org/W2144499799","https://openalex.org/W2166209411","https://openalex.org/W2398352100","https://openalex.org/W2757445263","https://openalex.org/W4285719527","https://openalex.org/W6608434954","https://openalex.org/W6630493826","https://openalex.org/W6664807928","https://openalex.org/W6681794868","https://openalex.org/W6712674617","https://openalex.org/W7048126131"],"related_works":["https://openalex.org/W1964208564","https://openalex.org/W169038075","https://openalex.org/W2547262076","https://openalex.org/W2103031592","https://openalex.org/W2563421448","https://openalex.org/W2774154397","https://openalex.org/W1565566036","https://openalex.org/W2921513691","https://openalex.org/W2534043196","https://openalex.org/W2098101267"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,48,96,108],"novel":[3],"and":[4,102,127],"unique":[5],"combination":[6,97],"of":[7,13,34,98,121,124,152],"algorithms":[8],"to":[9,55,87,107,137],"detect":[10],"the":[11,14,29,45,57,64,116,119,150,153],"gender":[12,129,151],"leading":[15,58,99],"vocalist":[16,128,155],"in":[17,90,148],"recorded":[18],"popular":[19],"music.":[20],"Building":[21],"on":[22,44,115,130,156],"our":[23,164],"previous":[24,165],"successful":[25],"approach":[26,110],"that":[27],"enhanced":[28],"harmonic":[30],"parts":[31],"by":[32,135],"means":[33],"Non-Negative":[35],"Matrix":[36],"Factorization":[37],"(NMF)":[38],"for":[39,80],"increased":[40],"accuracy,":[41],"we":[42,67,144],"integrate":[43],"one":[46],"hand":[47],"new":[49],"source":[50],"separation":[51,101],"algorithm":[52],"specifically":[53],"tailored":[54],"extracting":[56],"voice":[59,100],"from":[60],"monaural":[61],"recordings.":[62],"On":[63],"other":[65],"hand,":[66],"introduce":[68],"Bidirectional":[69],"Long":[70],"Short-Term":[71],"Memory":[72],"Recurrent":[73],"Neural":[74],"Networks":[75],"(BLSTM-RNNs)":[76],"as":[77,105],"context-sensitive":[78],"classifiers":[79],"this":[81,142],"scenario,":[82],"which":[83,159],"have":[84],"lately":[85],"led":[86],"great":[88],"success":[89],"Music":[91],"Information":[92],"Retrieval":[93],"tasks.":[94],"Through":[95],"BLSTM":[103],"networks,":[104],"opposed":[106],"baseline":[109],"using":[111,141],"Hidden":[112],"Naive":[113],"Bayes":[114],"original":[117],"recordings,":[118],"accuracy":[120,147],"simultaneous":[122],"detection":[123],"vocal":[125],"presence":[126],"beat":[131],"level":[132],"is":[133,160],"improved":[134],"up":[136],"10%":[138],"absolute.":[139],"Furthermore,":[140],"technique":[143],"achieve":[145],"91.6%":[146],"determining":[149],"predominant":[154],"song":[157],"level,":[158],"4%":[161],"absolute":[162],"above":[163],"best":[166],"result.":[167]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}