{"id":"https://openalex.org/W3082212277","doi":"https://doi.org/10.1109/spcom50965.2020.9179626","title":"Predominant Instrument Recognition in Polyphonic Music Using GMM-DNN Framework","display_name":"Predominant Instrument Recognition in Polyphonic Music Using GMM-DNN Framework","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3082212277","doi":"https://doi.org/10.1109/spcom50965.2020.9179626","mag":"3082212277"},"language":"en","primary_location":{"id":"doi:10.1109/spcom50965.2020.9179626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom50965.2020.9179626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Signal Processing and Communications (SPCOM)","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/A5036189122","display_name":"Roshni Ajayakumar","orcid":null},"institutions":[{"id":"https://openalex.org/I177436651","display_name":"Mahatma Gandhi University","ror":"https://ror.org/00h4spn88","country_code":"IN","type":"education","lineage":["https://openalex.org/I177436651"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Roshni Ajayakumar","raw_affiliation_strings":["Rajiv Gandhi Institute of Technology, Kottayam, India"],"affiliations":[{"raw_affiliation_string":"Rajiv Gandhi Institute of Technology, Kottayam, India","institution_ids":["https://openalex.org/I177436651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037326521","display_name":"Rajeev Rajan","orcid":"https://orcid.org/0000-0002-9489-859X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rajeev Rajan","raw_affiliation_strings":["College of Engineering, Trivandrum, Thiruvananthapuram, India"],"affiliations":[{"raw_affiliation_string":"College of Engineering, Trivandrum, Thiruvananthapuram, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5036189122"],"corresponding_institution_ids":["https://openalex.org/I177436651"],"apc_list":null,"apc_paid":null,"fwci":0.9123,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.7446212,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T13996","display_name":"Diverse Musicological Studies","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9958999752998352,"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":0.8457193374633789},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.7156177163124084},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7129673361778259},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.6318403482437134},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5797038674354553},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5686548948287964},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5555527210235596},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5170215368270874},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5106156468391418},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5080876350402832},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.45893594622612},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4179728925228119},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.07227092981338501}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8457193374633789},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.7156177163124084},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7129673361778259},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.6318403482437134},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5797038674354553},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5686548948287964},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5555527210235596},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5170215368270874},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5106156468391418},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5080876350402832},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.45893594622612},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4179728925228119},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.07227092981338501},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/spcom50965.2020.9179626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom50965.2020.9179626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Signal Processing and Communications (SPCOM)","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":30,"referenced_works":["https://openalex.org/W409429913","https://openalex.org/W875533737","https://openalex.org/W1272306948","https://openalex.org/W1504129048","https://openalex.org/W1556327471","https://openalex.org/W1590102137","https://openalex.org/W1981374696","https://openalex.org/W1988068457","https://openalex.org/W2008066450","https://openalex.org/W2015433306","https://openalex.org/W2016215128","https://openalex.org/W2035204557","https://openalex.org/W2065147844","https://openalex.org/W2094833092","https://openalex.org/W2099760476","https://openalex.org/W2114708606","https://openalex.org/W2158691456","https://openalex.org/W2261407818","https://openalex.org/W2292368352","https://openalex.org/W2410860376","https://openalex.org/W2593528643","https://openalex.org/W2765658200","https://openalex.org/W2963647337","https://openalex.org/W3098670224","https://openalex.org/W6614244475","https://openalex.org/W6628322026","https://openalex.org/W6629978730","https://openalex.org/W6635274319","https://openalex.org/W6645523747","https://openalex.org/W6692946518"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W2048014685","https://openalex.org/W4385672897","https://openalex.org/W2370972896","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"the":[3,50,95,102,106,110],"predominant":[4,121],"instrument":[5,122],"recognition":[6],"in":[7,15,101,119,123],"polyphonic":[8,124],"music":[9],"is":[10,62],"addressed":[11],"using":[12,65,90],"timbral":[13,45,83,113],"descriptors":[14,114],"three":[16],"frameworks-Gaussian":[17],"mixture":[18],"model":[19],"(GMM),":[20],"deep":[21],"neural":[22],"network":[23],"(DNN),":[24],"and":[25,43,49,57,74,79,115],"hybrid":[26],"GMM-DNN.":[27],"Three":[28],"sets":[29],"of":[30,88,112],"features,":[31,37],"namely,":[32],"mel-frequency":[33],"cepstral":[34],"coefficient":[35],"(MFCC)":[36],"modified":[38],"group":[39],"delay":[40],"features":[41,46,93],"(MODGDF),":[42],"lowlevel":[44],"are":[47,52,76],"computed,":[48],"experiments":[51,108],"conducted":[53],"with":[54],"individual":[55],"set":[56],"its":[58],"early":[59],"integration.":[60],"Performance":[61],"systematically":[63],"evaluated":[64],"IRMAS":[66],"dataset.":[67],"The":[68],"results":[69],"obtained":[70],"for":[71],"GMM,":[72],"DNN,":[73],"GMM-DNN":[75],"65.60%,":[77],"85.60%,":[78],"93.20%,":[80],"respectively":[81],"on":[82,94],"feature":[84,96],"fusion.":[85],"Architectural":[86],"choice":[87],"DNN":[89,116],"GMM":[91],"derived":[92],"fusion":[97],"paradigm":[98],"showed":[99],"improvement":[100],"system":[103],"performance.":[104],"Thus,":[105],"proposed":[107],"demonstrate":[109],"potential":[111],"based":[117],"systems":[118],"recognizing":[120],"music.":[125]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}