{"id":"https://openalex.org/W2154100244","doi":"https://doi.org/10.1109/icmew.2013.6618387","title":"Leveraging structural information in music-speech dectection","display_name":"Leveraging structural information in music-speech dectection","publication_year":2013,"publication_date":"2013-07-01","ids":{"openalex":"https://openalex.org/W2154100244","doi":"https://doi.org/10.1109/icmew.2013.6618387","mag":"2154100244"},"language":"en","primary_location":{"id":"doi:10.1109/icmew.2013.6618387","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew.2013.6618387","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 Multimedia and Expo Workshops (ICMEW)","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/A5102341476","display_name":"Jinyu Han","orcid":"https://orcid.org/0009-0005-8484-8889"},"institutions":[{"id":"https://openalex.org/I169912796","display_name":"Grace (United States)","ror":"https://ror.org/03k4vk194","country_code":"US","type":"company","lineage":["https://openalex.org/I169912796"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jinyu Han","raw_affiliation_strings":["Media Technology Laboratory, Gracenote, Inc., Emeryville, CA, USA"],"affiliations":[{"raw_affiliation_string":"Media Technology Laboratory, Gracenote, Inc., Emeryville, CA, USA","institution_ids":["https://openalex.org/I169912796"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072869244","display_name":"Bob Coover","orcid":null},"institutions":[{"id":"https://openalex.org/I169912796","display_name":"Grace (United States)","ror":"https://ror.org/03k4vk194","country_code":"US","type":"company","lineage":["https://openalex.org/I169912796"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bob Coover","raw_affiliation_strings":["Media Technology Laboratory, Gracenote, Inc., Emeryville, CA, USA"],"affiliations":[{"raw_affiliation_string":"Media Technology Laboratory, Gracenote, Inc., Emeryville, CA, USA","institution_ids":["https://openalex.org/I169912796"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102341476"],"corresponding_institution_ids":["https://openalex.org/I169912796"],"apc_list":null,"apc_paid":null,"fwci":0.3192,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.60969896,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"12","issue":null,"first_page":"1","last_page":"6"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9937999844551086,"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/computer-science","display_name":"Computer science","score":0.8046329617500305},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7621228098869324},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6382588148117065},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5886434316635132},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5649279356002808},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5618201494216919},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5599716305732727},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.548244833946228},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5028018951416016},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4850277304649353},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.4491731822490692},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42359307408332825},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42005422711372375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4200012683868408},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3697078824043274},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3560466468334198}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8046329617500305},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7621228098869324},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6382588148117065},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5886434316635132},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5649279356002808},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5618201494216919},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5599716305732727},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.548244833946228},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5028018951416016},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4850277304649353},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.4491731822490692},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42359307408332825},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42005422711372375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4200012683868408},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3697078824043274},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3560466468334198},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmew.2013.6618387","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew.2013.6618387","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 Multimedia and Expo Workshops (ICMEW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W112506568","https://openalex.org/W1517805583","https://openalex.org/W1833279920","https://openalex.org/W1964726488","https://openalex.org/W2052872069","https://openalex.org/W2106055371","https://openalex.org/W2128838222","https://openalex.org/W2133990480","https://openalex.org/W2144037622","https://openalex.org/W2166481862","https://openalex.org/W2167665852","https://openalex.org/W2296101064","https://openalex.org/W3103913776","https://openalex.org/W6604592628","https://openalex.org/W6631040601","https://openalex.org/W6638563753","https://openalex.org/W6679311584","https://openalex.org/W6684458125","https://openalex.org/W6684552998","https://openalex.org/W6697018327"],"related_works":["https://openalex.org/W2496295964","https://openalex.org/W1976952689","https://openalex.org/W2336887028","https://openalex.org/W1984921740","https://openalex.org/W2070982348","https://openalex.org/W2365485488","https://openalex.org/W2231892291","https://openalex.org/W2910493550","https://openalex.org/W1911859126","https://openalex.org/W642007152"],"abstract_inverted_index":{"Detecting":[0],"music":[1,39,65],"or":[2,38],"speech":[3,37,63],"signals":[4,66],"in":[5,24,48,67,120,136],"an":[6,10,121],"audio":[7,84,122],"mixture":[8,50],"is":[9,18,97,114,134,143],"important":[11],"but":[12,43],"challenging":[13,17],"problem.":[14],"Even":[15],"more":[16],"detecting":[19,45,62],"when":[20],"both":[21],"are":[22],"present":[23],"a":[25,49,107],"signal":[26],"at":[27],"the":[28,59,68,80,87,102,117,147,153,169,174],"same":[29],"time.":[30],"This":[31],"problem":[32,60],"requires":[33],"not":[34],"only":[35],"discriminating":[36],"from":[40],"each":[41,71],"other":[42,131],"also":[44],"its":[46],"presence":[47,69],"with":[51,130],"interfering":[52],"signals.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57],"address":[58],"of":[61,70,83,89,126,177],"and":[64,106],"other.":[72],"We":[73],"focus":[74],"on":[75,158],"leveraging":[76],"features":[77,128,133],"that":[78],"capture":[79],"structural":[81,175],"properties":[82],"to":[85,99,145,151,172],"improve":[86],"performance":[88],"concurrent":[90],"music-speech":[91],"detection.":[92],"Continuous":[93],"Frequency":[94],"Activation":[95,112],"(CFA)":[96],"used":[98],"account":[100],"for":[101,116],"sustained":[103],"pitch/harmonic":[104],"activities,":[105],"new":[108],"feature":[109,149],"called":[110],"Transient":[111],"(TAC)":[113],"proposed":[115],"transient/percussive":[118],"activities":[119],"signal.":[123],"The":[124],"effectiveness":[125],"these":[127],"along":[129],"acoustic":[132],"evaluated":[135],"different":[137],"statistical":[138],"classification":[139],"schemes.":[140],"Feature":[141],"selection":[142],"conducted":[144],"select":[146],"best":[148],"set":[150],"maximize":[152],"detection":[154],"performance.":[155],"Experimental":[156],"results":[157],"real":[159],"world":[160],"broadcast":[161],"recordings":[162],"have":[163],"shown":[164],"significant":[165],"improvement":[166],"by":[167],"using":[168],"above":[170],"techniques":[171],"incorporate":[173],"information":[176],"audio.":[178]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}