{"id":"https://openalex.org/W2147405829","doi":"https://doi.org/10.1109/icme.2008.4607727","title":"Improvements in audio classification based on sinusoidal modeling","display_name":"Improvements in audio classification based on sinusoidal modeling","publication_year":2008,"publication_date":"2008-06-01","ids":{"openalex":"https://openalex.org/W2147405829","doi":"https://doi.org/10.1109/icme.2008.4607727","mag":"2147405829"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2008.4607727","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2008.4607727","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Multimedia and Expo","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/A5057956688","display_name":"Jalil Shirazi","orcid":"https://orcid.org/0000-0001-7334-5067"},"institutions":[{"id":"https://openalex.org/I110525433","display_name":"Islamic Azad University, Tehran","ror":"https://ror.org/01kzn7k21","country_code":"IR","type":"education","lineage":["https://openalex.org/I110525433"]},{"id":"https://openalex.org/I4210101211","display_name":"University of Gonabad","ror":"https://ror.org/0161hbt42","country_code":"IR","type":"education","lineage":["https://openalex.org/I4210101211"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Jalil Shirazi","raw_affiliation_strings":["Gonabad Branch, Islamic Azad University, Iran","Islamic Azad University, Gonabad"],"affiliations":[{"raw_affiliation_string":"Gonabad Branch, Islamic Azad University, Iran","institution_ids":["https://openalex.org/I4210101211","https://openalex.org/I110525433"]},{"raw_affiliation_string":"Islamic Azad University, Gonabad","institution_ids":["https://openalex.org/I4210101211","https://openalex.org/I110525433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043485825","display_name":"Shahrokh Ghaemmaghami","orcid":"https://orcid.org/0000-0002-9556-8090"},"institutions":[{"id":"https://openalex.org/I133529467","display_name":"Sharif University of Technology","ror":"https://ror.org/024c2fq17","country_code":"IR","type":"education","lineage":["https://openalex.org/I133529467"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Shahrokh Ghaemmaghami","raw_affiliation_strings":["Sharif University of Technology, Iran"],"affiliations":[{"raw_affiliation_string":"Sharif University of Technology, Iran","institution_ids":["https://openalex.org/I133529467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043307061","display_name":"Farbod Razzazi","orcid":"https://orcid.org/0000-0003-4970-8117"},"institutions":[{"id":"https://openalex.org/I155419210","display_name":"Islamic Azad University, Science and Research Branch","ror":"https://ror.org/03187yj51","country_code":"IR","type":"education","lineage":["https://openalex.org/I110525433","https://openalex.org/I155419210"]},{"id":"https://openalex.org/I110525433","display_name":"Islamic Azad University, Tehran","ror":"https://ror.org/01kzn7k21","country_code":"IR","type":"education","lineage":["https://openalex.org/I110525433"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Farbod Razzazi","raw_affiliation_strings":["Science and Research Branch, Islamic Azad University, Iran","Islamic Azad Univ.-Sci. & Res. Branch, Iran"],"affiliations":[{"raw_affiliation_string":"Science and Research Branch, Islamic Azad University, Iran","institution_ids":["https://openalex.org/I155419210"]},{"raw_affiliation_string":"Islamic Azad Univ.-Sci. & Res. Branch, Iran","institution_ids":["https://openalex.org/I110525433"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5057956688"],"corresponding_institution_ids":["https://openalex.org/I110525433","https://openalex.org/I4210101211"],"apc_list":null,"apc_paid":null,"fwci":1.1198,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.79722001,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1485","last_page":"1488"},"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":0.9983999729156494,"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":0.984000027179718,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8252670764923096},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.694446325302124},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6170372366905212},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5899392366409302},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5377938747406006},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.515622079372406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5058083534240723},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.47379443049430847},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4676852822303772},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.46448999643325806},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4387706518173218},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4118335247039795},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3765002489089966},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3083541691303253}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8252670764923096},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.694446325302124},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6170372366905212},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5899392366409302},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5377938747406006},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.515622079372406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5058083534240723},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.47379443049430847},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4676852822303772},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.46448999643325806},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4387706518173218},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4118335247039795},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3765002489089966},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3083541691303253},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2008.4607727","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2008.4607727","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2106055371","https://openalex.org/W2110458017","https://openalex.org/W2115506669","https://openalex.org/W2128838222","https://openalex.org/W2131981197","https://openalex.org/W2147292340","https://openalex.org/W2149241068","https://openalex.org/W2154221499","https://openalex.org/W2164764235","https://openalex.org/W4402491236"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948","https://openalex.org/W2140099343","https://openalex.org/W2167481420"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3,101],"set":[4,102],"of":[5,15,23,41,49,71,75,103],"features":[6,33,44],"is":[7,45],"presented":[8],"and":[9,20,29,53,60],"evaluated":[10,46],"based":[11],"on":[12],"sinusoidal":[13,25,42,77,105],"modeling":[14],"audio":[16,36,50,90,113,133],"signals.":[17],"Amplitude,":[18],"frequency,":[19],"phase":[21],"parameters":[22,74],"the":[24,58,61,72,76,84,95,112,125,131],"model":[26,43],"are":[27],"used":[28,82],"compared":[30,93,119],"as":[31,92,118,128],"input":[32],"into":[34,51],"an":[35,89],"classifier":[37],"system.":[38],"The":[39],"performance":[40],"for":[47,83,87],"classification":[48,114],"speech":[52],"music":[54],"classes":[55],"using":[56,100],"both":[57],"Gaussian":[59],"GMM":[62],"(Gaussian":[63],"mixture":[64],"model)":[65],"classifiers.":[66],"Experimental":[67],"results":[68],"show":[69],"superiority":[70],"amplitude":[73],"model,":[78],"which":[79],"could":[80],"be":[81],"first":[85],"time":[86],"such":[88],"classification,":[91],"to":[94,120],"popular":[96],"cepstral":[97],"features.":[98],"By":[99],"40":[104],"features,":[106],"we":[107],"achieved":[108],"95.06%":[109],"accuracy":[110,122],"in":[111],"at":[115],"frame":[116],"level,":[117],"92.26%":[121],"obtained":[123],"with":[124],"MFCC":[126],"coefficients,":[127],"tested":[129],"over":[130],"same":[132],"corpus.":[134]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}