{"id":"https://openalex.org/W2207196656","doi":"https://doi.org/10.1109/eusipco.2015.7362337","title":"A low-latency, real-time-capable singing voice detection method with LSTM recurrent neural networks","display_name":"A low-latency, real-time-capable singing voice detection method with LSTM recurrent neural networks","publication_year":2015,"publication_date":"2015-08-01","ids":{"openalex":"https://openalex.org/W2207196656","doi":"https://doi.org/10.1109/eusipco.2015.7362337","mag":"2207196656"},"language":"en","primary_location":{"id":"doi:10.1109/eusipco.2015.7362337","is_oa":false,"landing_page_url":"https://doi.org/10.1109/eusipco.2015.7362337","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 23rd European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},"type":"article","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/A5053582419","display_name":"Bernhard Lehner","orcid":"https://orcid.org/0000-0002-7754-7042"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Bernhard Lehner","raw_affiliation_strings":["Department of Computational Perception, Johannes Kepler University of Linz, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computational Perception, Johannes Kepler University of Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003768123","display_name":"Gerhard Widmer","orcid":"https://orcid.org/0000-0003-3531-1282"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Gerhard Widmer","raw_affiliation_strings":["Department of Computational Perception, Johannes Kepler University of Linz, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computational Perception, Johannes Kepler University of Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089048082","display_name":"Sebastian B\u00f6ck","orcid":"https://orcid.org/0000-0001-6707-5427"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Sebastian Bock","raw_affiliation_strings":["Department of Computational Perception, Johannes Kepler University of Linz, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computational Perception, Johannes Kepler University of Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.5093,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.96480534,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"2","issue":null,"first_page":"21","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/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":0.9980000257492065,"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/computer-science","display_name":"Computer science","score":0.8145452737808228},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.7944959402084351},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7919600009918213},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.7688035368919373},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6442027688026428},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5537126660346985},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5054001808166504},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5006561279296875},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4768420457839966},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43963855504989624},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42604827880859375},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.42294588685035706},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07045102119445801}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8145452737808228},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.7944959402084351},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7919600009918213},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7688035368919373},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6442027688026428},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5537126660346985},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5054001808166504},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5006561279296875},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4768420457839966},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43963855504989624},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42604827880859375},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.42294588685035706},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07045102119445801},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/eusipco.2015.7362337","is_oa":false,"landing_page_url":"https://doi.org/10.1109/eusipco.2015.7362337","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 23rd European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1519655822","https://openalex.org/W1999454387","https://openalex.org/W2007664495","https://openalex.org/W2054985402","https://openalex.org/W2064675550","https://openalex.org/W2079735306","https://openalex.org/W2085662862","https://openalex.org/W2098796164","https://openalex.org/W2144499799","https://openalex.org/W2288351922","https://openalex.org/W2293137601","https://openalex.org/W2350911425","https://openalex.org/W2406220897","https://openalex.org/W4285719527","https://openalex.org/W6631117800","https://openalex.org/W6696493858","https://openalex.org/W6697162658","https://openalex.org/W6713299141"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W3205411230","https://openalex.org/W4286899009","https://openalex.org/W9168048","https://openalex.org/W4300849822","https://openalex.org/W4376480820","https://openalex.org/W3155891479","https://openalex.org/W3029351463","https://openalex.org/W4308600690"],"abstract_inverted_index":{"Singing":[0],"voice":[1,76,115],"detection":[2],"aims":[3],"at":[4,13,126],"identifying":[5],"the":[6,29,33,84,90,112,118,127,135,139],"regions":[7],"in":[8,89,121],"a":[9,20,95],"music":[10],"recording":[11],"where":[12],"least":[14],"one":[15],"person":[16],"sings.":[17],"This":[18,55],"is":[19,67,72],"challenging":[21],"problem":[22,81],"that":[23,97],"cannot":[24],"be":[25],"solved":[26],"without":[27],"analysing":[28],"temporal":[30,41],"evolution":[31],"of":[32,123,138],"signal.":[34],"Current":[35],"state-of-the-art":[36,119],"methods":[37],"combine":[38],"timbral":[39],"with":[40],"characteristics,":[42],"by":[43,51],"summarising":[44],"various":[45],"feature":[46],"values":[47],"over":[48],"time,":[49],"e.g.":[50],"computing":[52],"their":[53],"variance.":[54],"leads":[56],"to":[57,63,86],"more":[58],"contextual":[59],"information,":[60],"but":[61],"also":[62],"increased":[64],"latency,":[65],"which":[66],"problematic":[68],"if":[69],"our":[70],"goal":[71],"on-line,":[73],"real-time":[74],"singing":[75,114],"detection.":[77],"To":[78],"overcome":[79],"this":[80],"and":[82,133],"reduce":[83],"necessity":[85],"include":[87],"context":[88],"features":[91],"themselves,":[92],"we":[93],"introduce":[94],"method":[96],"uses":[98],"Long":[99],"Short-Term":[100],"Memory":[101],"Recurrent":[102],"Neural":[103],"Networks":[104],"(LSTM-RNN).":[105],"In":[106],"experiments":[107],"on":[108],"several":[109],"data":[110],"sets,":[111],"resulting":[113],"detector":[116],"outperforms":[117],"baselines":[120],"terms":[122],"accuracy,":[124],"while":[125],"same":[128],"time":[129,136],"drastically":[130],"reducing":[131],"latency":[132],"increasing":[134],"resolution":[137],"detector.":[140]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}