{"id":"https://openalex.org/W1533548161","doi":"https://doi.org/10.1186/s13636-015-0062-9","title":"Singer identification using perceptual features and cepstral coefficients of an audio signal from Indian video songs","display_name":"Singer identification using perceptual features and cepstral coefficients of an audio signal from Indian video songs","publication_year":2015,"publication_date":"2015-06-24","ids":{"openalex":"https://openalex.org/W1533548161","doi":"https://doi.org/10.1186/s13636-015-0062-9","mag":"1533548161"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-015-0062-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-015-0062-9","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-015-0062-9","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-015-0062-9","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086198045","display_name":"Tushar V. Ratanpara","orcid":null},"institutions":[{"id":"https://openalex.org/I1320404931","display_name":"C. U. Shah University","ror":"https://ror.org/04rt7n757","country_code":"IN","type":"education","lineage":["https://openalex.org/I1320404931"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Tushar Ratanpara","raw_affiliation_strings":["C. U. Shah University, Wadhwan, Gujarat, India","C.U. Shah Univ., Wadhwan, India"],"affiliations":[{"raw_affiliation_string":"C. U. Shah University, Wadhwan, Gujarat, India","institution_ids":["https://openalex.org/I1320404931"]},{"raw_affiliation_string":"C.U. Shah Univ., Wadhwan, India","institution_ids":["https://openalex.org/I1320404931"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111117966","display_name":"Narendra Patel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Narendra Patel","raw_affiliation_strings":["Birla Vishwakarma Vidhyalaya, v.v. nagar, India"],"affiliations":[{"raw_affiliation_string":"Birla Vishwakarma Vidhyalaya, v.v. nagar, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086198045"],"corresponding_institution_ids":["https://openalex.org/I1320404931"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":2.0103,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.86485541,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"2015","issue":"1","first_page":null,"last_page":null},"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":0.9966999888420105,"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":0.9836000204086304,"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":0.7451019883155823},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.742459774017334},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.7262320518493652},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6285055875778198},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5776652097702026},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5443751811981201},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.5312390327453613},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49806785583496094},{"id":"https://openalex.org/keywords/loudness","display_name":"Loudness","score":0.48460209369659424},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.45968765020370483},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.4596386253833771},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.44771212339401245},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.4475232660770416},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42226338386535645},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.41386228799819946},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.38154762983322144},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.17103391885757446},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.15046349167823792}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7451019883155823},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.742459774017334},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.7262320518493652},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6285055875778198},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5776652097702026},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5443751811981201},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.5312390327453613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49806785583496094},{"id":"https://openalex.org/C79018884","wikidata":"https://www.wikidata.org/wiki/Q622324","display_name":"Loudness","level":2,"score":0.48460209369659424},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.45968765020370483},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.4596386253833771},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.44771212339401245},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.4475232660770416},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42226338386535645},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.41386228799819946},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.38154762983322144},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.17103391885757446},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.15046349167823792},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1186/s13636-015-0062-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-015-0062-9","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-015-0062-9","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1186/s13636-015-0062-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-015-0062-9","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-015-0062-9","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Gender equality","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1533548161.pdf","grobid_xml":"https://content.openalex.org/works/W1533548161.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W15066456","https://openalex.org/W33139900","https://openalex.org/W49012378","https://openalex.org/W255556494","https://openalex.org/W1515616414","https://openalex.org/W1523138083","https://openalex.org/W1537933855","https://openalex.org/W1543301896","https://openalex.org/W1595053282","https://openalex.org/W1633848179","https://openalex.org/W1800584916","https://openalex.org/W1986061641","https://openalex.org/W1988790447","https://openalex.org/W2012978316","https://openalex.org/W2038101708","https://openalex.org/W2057428615","https://openalex.org/W2059857061","https://openalex.org/W2063339519","https://openalex.org/W2067640805","https://openalex.org/W2083383166","https://openalex.org/W2097798376","https://openalex.org/W2107252339","https://openalex.org/W2117892041","https://openalex.org/W2128117472","https://openalex.org/W2128980425","https://openalex.org/W2148135014","https://openalex.org/W2152575748","https://openalex.org/W2157075290","https://openalex.org/W2157306219","https://openalex.org/W2158143121","https://openalex.org/W2170067073","https://openalex.org/W2187730514","https://openalex.org/W2558906580","https://openalex.org/W3145004415","https://openalex.org/W4212835817","https://openalex.org/W4285719527","https://openalex.org/W6850522384"],"related_works":["https://openalex.org/W1107690805","https://openalex.org/W2097318409","https://openalex.org/W2739662815","https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2787035864","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W106160982"],"abstract_inverted_index":{"Singer":[0],"identification":[1],"is":[2,14,34,144,156,182],"a":[3,23,58],"difficult":[4],"topic":[5],"in":[6,53],"music":[7,13],"information":[8],"retrieval":[9],"because":[10],"background":[11],"instrumental":[12,37,62],"included":[15],"with":[16,196],"singing":[17,64],"voice":[18],"which":[19],"reduces":[20],"performance":[21],"of":[22,26,30,86,98,130,140,187,192],"system.":[24],"One":[25],"the":[27,31],"main":[28],"disadvantages":[29],"existing":[32],"system":[33],"vocals":[35,43],"and":[36,41,63,84,125,174,189,200],"are":[38,44,103,134],"separated":[39],"manually":[40],"only":[42],"used":[45],"to":[46],"build":[47],"training":[48],"model.":[49],"The":[50,179],"research":[51],"presented":[52],"this":[54],"paper":[55],"automatically":[56],"recognize":[57],"singer":[59,153],"without":[60],"separating":[61],"sounds":[65],"using":[66,146,158],"audio":[67,88,108,113,132,142,193],"features":[68,109,143],"like":[69,162],"timbre":[70,112],"coefficients,":[71,83,121,124],"pitch":[72,117],"class,":[73],"mel":[74],"frequency":[75],"cepstral":[76],"coefficients":[77],"(MFCC),":[78],"linear":[79],"predictive":[80],"coding":[81],"(LPC)":[82],"loudness":[85,127],"an":[87,131],"signal":[89],"from":[90,136],"Indian":[91,198],"video":[92],"songs":[93],"(IVS).":[94],"Initially,":[95],"various":[96,185,197],"IVS":[97],"distinct":[99],"playback":[100],"singers":[101],"(PS)":[102],"collected.":[104],"After":[105],"that,":[106],"53":[107],"(12":[110],"dimensional":[111],"feature":[114,128,194],"vectors,":[115],"12":[116],"classes,":[118],"13":[119,122],"MFCC":[120],"LPC":[123],"3":[126],"vector":[129],"signal)":[133],"extracted":[135,141],"each":[137],"segment.":[138],"Dimension":[139],"reduced":[145],"principal":[147],"component":[148],"analysis":[149],"(PCA)":[150],"method.":[151],"Playback":[152],"model":[154,177],"(PSM)":[155],"trained":[157],"multiclass":[159],"classification":[160],"algorithms":[161],"back":[163],"propagation,":[164],"AdaBoost.M2,":[165],"k-nearest":[166],"neighbor":[167],"(KNN)":[168],"algorithm,":[169],"na\u00efve":[170],"Bayes":[171],"classifier":[172],"(NBC),":[173],"Gaussian":[175],"mixture":[176],"(GMM).":[178],"proposed":[180],"approach":[181],"tested":[183],"on":[184],"combinations":[186,191],"dataset":[188],"different":[190],"vectors":[195],"male":[199],"female":[201],"PS\u2019s":[202],"songs.":[203]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}