{"id":"https://openalex.org/W1516543035","doi":"https://doi.org/10.1109/icassp.2015.7177958","title":"Multi-instrument detection in polyphonic music using Gaussian Mixture based factorial HMM","display_name":"Multi-instrument detection in polyphonic music using Gaussian Mixture based factorial HMM","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1516543035","doi":"https://doi.org/10.1109/icassp.2015.7177958","mag":"1516543035"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7177958","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7177958","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5035716225","display_name":"H. G. Ranjani","orcid":"https://orcid.org/0000-0002-4202-2967"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"H. G. Ranjani","raw_affiliation_strings":["Dept. of ECE., Indian Institute of Science, Bangalore, Karnataka, IN","Department of ECE, Indian Institute of Science, Bangalore 560 012, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of ECE., Indian Institute of Science, Bangalore, Karnataka, IN","institution_ids":["https://openalex.org/I59270414"]},{"raw_affiliation_string":"Department of ECE, Indian Institute of Science, Bangalore 560 012, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069425803","display_name":"T.V. Sreenivas","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"T. V. Sreenivas","raw_affiliation_strings":["Dept. of ECE, Indian Institute of Science, Bangalore, India","Department of ECE, Indian Institute of Science, Bangalore 560 012, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of ECE, Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]},{"raw_affiliation_string":"Department of ECE, Indian Institute of Science, Bangalore 560 012, India","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":0.2842,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.51982612,"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":"191","last_page":"195"},"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":0.9994999766349792,"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":0.9980999827384949,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.9246219396591187},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.7724785804748535},{"id":"https://openalex.org/keywords/factorial","display_name":"Factorial","score":0.6716152429580688},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.58841872215271},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5588257312774658},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5522373914718628},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5507300496101379},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5474111437797546},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.516179621219635},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.491294801235199},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46977299451828003},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4552854001522064},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4388086795806885},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33103102445602417},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23363837599754333},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.21554160118103027},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.07905170321464539}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.9246219396591187},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.7724785804748535},{"id":"https://openalex.org/C183763347","wikidata":"https://www.wikidata.org/wiki/Q120976","display_name":"Factorial","level":2,"score":0.6716152429580688},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.58841872215271},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5588257312774658},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5522373914718628},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5507300496101379},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5474111437797546},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.516179621219635},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.491294801235199},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46977299451828003},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4552854001522064},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4388086795806885},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33103102445602417},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23363837599754333},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.21554160118103027},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.07905170321464539},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2015.7177958","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7177958","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.iisc.ac.in:53292","is_oa":false,"landing_page_url":"http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=7177958&abstractAccess=no&userType=inst","pdf_url":null,"source":{"id":"https://openalex.org/S4377196309","display_name":"NOT FOUND REPOSITORY (Indian Institute of Science Bangalore)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceedings"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W180338449","https://openalex.org/W1272306948","https://openalex.org/W1528056001","https://openalex.org/W1574263887","https://openalex.org/W1607142029","https://openalex.org/W1801637500","https://openalex.org/W1846203979","https://openalex.org/W1970423186","https://openalex.org/W2011089476","https://openalex.org/W2017416504","https://openalex.org/W2045036776","https://openalex.org/W2098571827","https://openalex.org/W2099168659","https://openalex.org/W2103189252","https://openalex.org/W2104484487","https://openalex.org/W2114708606","https://openalex.org/W2115680399","https://openalex.org/W2120809168","https://openalex.org/W2124776405","https://openalex.org/W2129258718","https://openalex.org/W2132543170","https://openalex.org/W2136785699","https://openalex.org/W2147834639","https://openalex.org/W2150415460","https://openalex.org/W2155531311","https://openalex.org/W2186196505","https://openalex.org/W2242076280","https://openalex.org/W2406447034","https://openalex.org/W4285719527","https://openalex.org/W6607291369","https://openalex.org/W6628322026","https://openalex.org/W6636203886","https://openalex.org/W6638777396","https://openalex.org/W6681822791","https://openalex.org/W6686287241","https://openalex.org/W6713863964"],"related_works":["https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W4200063482","https://openalex.org/W2357575019","https://openalex.org/W2370117122","https://openalex.org/W2360603947","https://openalex.org/W2371528275","https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2160650576"],"abstract_inverted_index":{"We":[0,34,77,93],"formulate":[1],"the":[2,6,40,59,65,80,126,142],"problem":[3],"of":[4,61,84,96,101],"detecting":[5],"constituent":[7],"instruments":[8],"in":[9,43,64,108,146],"a":[10,15,36,44],"polyphonic":[11],"music":[12],"piece":[13],"as":[14,48],"joint":[16,81],"decoding":[17],"problem.":[18],"From":[19],"monophonic":[20],"data,":[21],"parametric":[22],"Gaussian":[23],"Mixture":[24],"Hidden":[25],"Markov":[26],"Models":[27],"(GM-HMM)":[28],"are":[29,54,71],"obtained":[30],"for":[31],"each":[32,62],"instrument.":[33],"propose":[35],"method":[37,98],"to":[38,57,117],"use":[39],"above":[41],"models":[42,123,145],"factorial":[45],"framework,":[46],"termed":[47],"Factorial":[49],"GM-HMM":[50,107],"(F-GM-HMM).":[51],"The":[52,69],"states":[53,87],"jointly":[55],"inferred":[56],"explain":[58],"evolution":[60,83],"instrument":[63,122],"mixture":[66,103],"observation":[67],"sequence.":[68],"dependencies":[70],"decoupled":[72],"using":[73,91],"variational":[74],"inference":[75],"technique.":[76],"show":[78,135],"that":[79,100,136],"time":[82],"all":[85],"instruments'":[86],"can":[88],"be":[89],"captured":[90],"F-GM-HMM.":[92],"compare":[94],"performance":[95],"proposed":[97],"with":[99,120],"Student's-t":[102],"model":[104],"(tMM)":[105],"and":[106,132],"an":[109,139],"existing":[110],"latent":[111],"variable":[112],"framework.":[113],"Experiments":[114],"on":[115,125,130],"two":[116],"five":[118],"polyphony":[119],"8":[121],"trained":[124],"RWC":[127,131],"dataset,":[128],"tested":[129],"TRIOS":[133],"datasets":[134],"F-GM-HMM":[137],"gives":[138],"advantage":[140],"over":[141],"other":[143],"considered":[144],"segments":[147],"containing":[148],"co-occurring":[149],"instruments.":[150]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}