{"id":"https://openalex.org/W2033573285","doi":"https://doi.org/10.1109/slt.2014.7078609","title":"Discrimination between singing and speech in real-world audio","display_name":"Discrimination between singing and speech in real-world audio","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2033573285","doi":"https://doi.org/10.1109/slt.2014.7078609","mag":"2033573285"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2014.7078609","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","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/A5105836462","display_name":"Brian J. Thompson","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]},{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Brian Thompson","raw_affiliation_strings":["MIT Lincoln Laboratory, Lexington, Massachusetts","MIT Lincoln Laboratory, Lexington, Massachusetts, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory, Lexington, Massachusetts","institution_ids":["https://openalex.org/I4210122954"]},{"raw_affiliation_string":"MIT Lincoln Laboratory, Lexington, Massachusetts, USA#TAB#","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5105836462"],"corresponding_institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.10381344,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"407","last_page":"412"},"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":0.9998000264167786,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9962000250816345,"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/singing","display_name":"Singing","score":0.8698570728302002},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7802327275276184},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.717553973197937},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.614216148853302},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5131385922431946},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.497724324464798},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4816645383834839},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.4484281539916992},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3631363809108734},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.19134142994880676}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8698570728302002},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7802327275276184},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.717553973197937},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.614216148853302},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5131385922431946},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.497724324464798},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4816645383834839},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.4484281539916992},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3631363809108734},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.19134142994880676},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2014.7078609","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W155077236","https://openalex.org/W188353524","https://openalex.org/W1486187507","https://openalex.org/W1553896573","https://openalex.org/W1833279920","https://openalex.org/W1990346118","https://openalex.org/W2002887418","https://openalex.org/W2048752878","https://openalex.org/W2051981399","https://openalex.org/W2106055371","https://openalex.org/W2123368707","https://openalex.org/W2124864596","https://openalex.org/W2128838222","https://openalex.org/W2130426352","https://openalex.org/W2134237567","https://openalex.org/W2141732083","https://openalex.org/W2151305614","https://openalex.org/W6606312984","https://openalex.org/W6629185806"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795","https://openalex.org/W2366077683","https://openalex.org/W2284826389","https://openalex.org/W1485516824"],"abstract_inverted_index":{"The":[0,66,86],"performance":[1],"of":[2,51,83],"a":[3,31,39,54,63,70,94,140],"spoken":[4],"language":[5],"system":[6],"suffers":[7],"when":[8,137],"non-speech":[9],"is":[10,16,58,90,110,126],"incorrectly":[11],"classified":[12],"as":[13,120],"speech.":[14],"Singing":[15],"particularly":[17],"difficult":[18],"to":[19,60,73,106,117,128],"discriminate":[20],"from":[21,47],"speech,":[22],"since":[23],"both":[24],"are":[25],"natural":[26],"language.":[27],"However,":[28],"singing":[29,76,89,135],"conveys":[30],"melody,":[32],"whereas":[33],"speech":[34,78,133],"does":[35],"not;":[36],"in":[37,88],"particular,":[38],"singer's":[40],"fundamental":[41,56],"frequency":[42,57],"should":[43],"not":[44,92],"deviate":[45,61],"significantly":[46],"an":[48,104],"underlying":[49],"sequence":[50],"notes,":[52],"while":[53],"speaker's":[55],"freer":[59],"about":[62],"mean":[64],"value.":[65],"present":[67],"work":[68,147],"presents":[69],"novel":[71],"approach":[72],"discrimination":[74],"between":[75,132],"and":[77,134],"that":[79,112],"exploits":[80],"the":[81,97,114],"distribution":[82,98],"such":[84],"deviations.":[85],"melody":[87,116],"typically":[91],"known":[93],"priori,":[95],"so":[96],"cannot":[99],"be":[100,118,129],"measured":[101],"directly.":[102],"Instead,":[103],"approximation":[105],"its":[107],"Fourier":[108],"transform":[109],"proposed":[111],"allows":[113],"unknown":[115],"treated":[119],"multiplicative":[121],"noise.":[122],"This":[123],"feature":[124],"vector":[125],"shown":[127],"highly":[130],"discriminative":[131],"segments":[136],"coupled":[138],"with":[139],"simple":[141],"maximum":[142],"likelihood":[143],"classifier,":[144],"outperforming":[145],"prior":[146],"on":[148],"real-world":[149],"data.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-25T21:42:39.735039","created_date":"2025-10-10T00:00:00"}