{"id":"https://openalex.org/W1999454387","doi":"https://doi.org/10.1109/icassp.2013.6637694","title":"Real-life voice activity detection with LSTM Recurrent Neural Networks and an application to Hollywood movies","display_name":"Real-life voice activity detection with LSTM Recurrent Neural Networks and an application to Hollywood movies","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W1999454387","doi":"https://doi.org/10.1109/icassp.2013.6637694","mag":"1999454387"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6637694","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6637694","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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=1189651","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023264395","display_name":"Florian Eyben","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094487","display_name":"Intel (Germany)","ror":"https://ror.org/00m2x0g47","country_code":"DE","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210094487"]},{"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":["Machine Intelligence & Signal Processing Group, MMK, Techische Universit\u00e4t M\u00fcnchen, Germany","Machine Intell. & Signal Process. Group, Techische Univ. Munchen, Mu\u0308nchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Intelligence & Signal Processing Group, MMK, Techische Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Machine Intell. & Signal Process. Group, Techische Univ. Munchen, Mu\u0308nchen, Germany","institution_ids":["https://openalex.org/I4210094487","https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016747567","display_name":"Felix Weninger","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094487","display_name":"Intel (Germany)","ror":"https://ror.org/00m2x0g47","country_code":"DE","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210094487"]},{"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":["Machine Intelligence & Signal Processing Group, MMK, Techische Universit\u00e4t M\u00fcnchen, Germany","Machine Intell. & Signal Process. Group, Techische Univ. Munchen, Mu\u0308nchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Intelligence & Signal Processing Group, MMK, Techische Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Machine Intell. & Signal Process. Group, Techische Univ. Munchen, Mu\u0308nchen, Germany","institution_ids":["https://openalex.org/I4210094487","https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034253968","display_name":"Stefano Squartini","orcid":"https://orcid.org/0000-0001-9374-0128"},"institutions":[{"id":"https://openalex.org/I122534668","display_name":"Marche Polytechnic University","ror":"https://ror.org/00x69rs40","country_code":"IT","type":"education","lineage":["https://openalex.org/I122534668"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Stefano Squartini","raw_affiliation_strings":["Department of Information Engineering, Universit\u00e0 Politecnica delle Marche, Ancona, Italy","Dept. of Inf. Eng., Univ. Politec. delle Marche, Ancona, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Universit\u00e0 Politecnica delle Marche, Ancona, Italy","institution_ids":["https://openalex.org/I122534668"]},{"raw_affiliation_string":"Dept. of Inf. Eng., Univ. Politec. delle Marche, Ancona, Italy","institution_ids":["https://openalex.org/I122534668"]}]},{"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/I4210094487","display_name":"Intel (Germany)","ror":"https://ror.org/00m2x0g47","country_code":"DE","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210094487"]},{"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":["Machine Intelligence & Signal Processing Group, MMK, Techische Universit\u00e4t M\u00fcnchen, Germany","Machine Intell. & Signal Process. Group, Techische Univ. Munchen, Mu\u0308nchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Intelligence & Signal Processing Group, MMK, Techische Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Machine Intell. & Signal Process. Group, Techische Univ. Munchen, Mu\u0308nchen, Germany","institution_ids":["https://openalex.org/I4210094487","https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":213,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"483","last_page":"487"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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/computer-science","display_name":"Computer science","score":0.7726786136627197},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.7503457069396973},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6768354177474976},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6263353228569031},{"id":"https://openalex.org/keywords/hollywood","display_name":"Hollywood","score":0.5658812522888184},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5471495985984802},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5401294827461243},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5229009985923767},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5031172633171082},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5024082660675049},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.47336694598197937},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4694019854068756},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4663609266281128},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43656036257743835},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.43042299151420593},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.28870752453804016},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.25175940990448},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09820437431335449},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08545231819152832}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7726786136627197},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7503457069396973},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6768354177474976},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6263353228569031},{"id":"https://openalex.org/C2780458788","wikidata":"https://www.wikidata.org/wiki/Q5882564","display_name":"Hollywood","level":2,"score":0.5658812522888184},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5471495985984802},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5401294827461243},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5229009985923767},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5031172633171082},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5024082660675049},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.47336694598197937},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4694019854068756},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4663609266281128},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43656036257743835},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.43042299151420593},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.28870752453804016},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.25175940990448},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09820437431335449},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08545231819152832},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C153911025","wikidata":"https://www.wikidata.org/wiki/Q7202","display_name":"Molecular biology","level":1,"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":3,"locations":[{"id":"doi:10.1109/icassp.2013.6637694","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6637694","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.univpm.it:11566/91063","is_oa":false,"landing_page_url":"http://hdl.handle.net/11566/91063","pdf_url":null,"source":{"id":"https://openalex.org/S4306402571","display_name":"Universit\u00e0 Politecnica delle Marche (Universit\u00e0 Politecnica delle Marche)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122534668","host_organization_name":"Marche Polytechnic University","host_organization_lineage":["https://openalex.org/I122534668"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1189651","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1189651","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/1189651","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1189651","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W159356774","https://openalex.org/W1685006559","https://openalex.org/W1899504021","https://openalex.org/W1995609724","https://openalex.org/W2032362923","https://openalex.org/W2051170812","https://openalex.org/W2064675550","https://openalex.org/W2085662862","https://openalex.org/W2090861223","https://openalex.org/W2098265087","https://openalex.org/W2112118016","https://openalex.org/W2115717467","https://openalex.org/W2129120544","https://openalex.org/W2136155127","https://openalex.org/W2140732925","https://openalex.org/W2146324387","https://openalex.org/W2158260978","https://openalex.org/W2398042456","https://openalex.org/W2401833940","https://openalex.org/W2402212287","https://openalex.org/W2403186097","https://openalex.org/W2406310406","https://openalex.org/W2407534391","https://openalex.org/W2408070479","https://openalex.org/W2783324411","https://openalex.org/W3127686677","https://openalex.org/W6631636882","https://openalex.org/W6713831699"],"related_works":["https://openalex.org/W2994894110","https://openalex.org/W4377862891","https://openalex.org/W2005708641","https://openalex.org/W2050397613","https://openalex.org/W2080458333","https://openalex.org/W1995562189","https://openalex.org/W172689163","https://openalex.org/W1507177964","https://openalex.org/W2145230572","https://openalex.org/W2611200336"],"abstract_inverted_index":{"A":[0,85],"novel,":[1],"data-driven":[2],"approach":[3,11,63],"to":[4],"voice":[5],"activity":[6],"detection":[7],"is":[8,12,64,93,104],"presented.":[9],"The":[10,62],"based":[13],"on":[14,22,66],"Long":[15],"Short-Term":[16],"Memory":[17],"Recurrent":[18],"Neural":[19],"Networks":[20],"trained":[21],"standard":[23],"RASTA-PLP":[24],"frontend":[25],"features.":[26],"To":[27],"approximate":[28],"real-life":[29,76],"scenarios,":[30],"large":[31],"amounts":[32],"of":[33,58,80,91,102,115],"noisy":[34],"speech":[35,45],"instances":[36],"are":[37],"mixed":[38,69],"by":[39],"using":[40],"both":[41],"read":[42],"and":[43,49,52,99],"spontaneous":[44],"from":[46],"the":[47,96,107,125],"TIMIT":[48],"Buckeye":[50],"corpora,":[51],"adding":[53],"real":[54],"long":[55],"term":[56],"recordings":[57],"diverse":[59],"noise":[60],"types.":[61],"evaluated":[65],"unseen":[67],"synthetically":[68],"test":[70,77,109],"data":[71,110],"as":[72,74],"well":[73],"a":[75,112],"set":[78],"consisting":[79],"four":[81,97],"full-length":[82],"Hollywood":[83],"movies.":[84],"frame-wise":[86],"Equal":[87],"Error":[88],"Rate":[89],"(EER)":[90],"33.2%":[92],"obtained":[94,105],"for":[95,106],"movies":[98],"an":[100],"EER":[101],"9.6%":[103],"synthetic":[108],"at":[111],"peak":[113],"SNR":[114],"0":[116],"dB,":[117],"clearly":[118],"outperforming":[119],"three":[120],"state-of-the-art":[121],"reference":[122],"algorithms":[123],"under":[124],"same":[126],"conditions.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":31},{"year":2019,"cited_by_count":34},{"year":2018,"cited_by_count":24},{"year":2017,"cited_by_count":23},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":5}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
