{"id":"https://openalex.org/W2604465723","doi":"https://doi.org/10.1109/taslp.2017.2690576","title":"Polyphonic Sound Event Tracking Using Linear Dynamical Systems","display_name":"Polyphonic Sound Event Tracking Using Linear Dynamical Systems","publication_year":2017,"publication_date":"2017-05-23","ids":{"openalex":"https://openalex.org/W2604465723","doi":"https://doi.org/10.1109/taslp.2017.2690576","mag":"2604465723"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2017.2690576","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2690576","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-01520194","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084672392","display_name":"Emmanouil Benetos","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Emmanouil Benetos","raw_affiliation_strings":["School of Electronic Engineering and Computer Science, Queen Mary University of London, London, U.K"],"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering and Computer Science, Queen Mary University of London, London, U.K","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069228309","display_name":"Gr\u00e9goire Lafay","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I100445878","display_name":"\u00c9cole Centrale de Nantes","ror":"https://ror.org/03nh7d505","country_code":"FR","type":"education","lineage":["https://openalex.org/I100445878","https://openalex.org/I97188460"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gregoire Lafay","raw_affiliation_strings":["IRCCYN, CNRS, \u00c9cole Centrale de Nantes, Nantes Cedex, France"],"affiliations":[{"raw_affiliation_string":"IRCCYN, CNRS, \u00c9cole Centrale de Nantes, Nantes Cedex, France","institution_ids":["https://openalex.org/I100445878","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029522748","display_name":"Mathieu Lagrange","orcid":"https://orcid.org/0000-0002-1253-4427"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I100445878","display_name":"\u00c9cole Centrale de Nantes","ror":"https://ror.org/03nh7d505","country_code":"FR","type":"education","lineage":["https://openalex.org/I100445878","https://openalex.org/I97188460"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mathieu Lagrange","raw_affiliation_strings":["IRCCYN, CNRS, \u00c9cole Centrale de Nantes, Nantes Cedex, France"],"affiliations":[{"raw_affiliation_string":"IRCCYN, CNRS, \u00c9cole Centrale de Nantes, Nantes Cedex, France","institution_ids":["https://openalex.org/I100445878","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066967599","display_name":"Mark D. Plumbley","orcid":"https://orcid.org/0000-0002-9708-1075"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark D. Plumbley","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5084672392"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":1.8691,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.86590117,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"25","issue":"6","first_page":"1266","last_page":"1277"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9954000115394592,"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":0.715984582901001},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6858606934547424},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.6662234663963318},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6418414115905762},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.50834721326828},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4840647280216217},{"id":"https://openalex.org/keywords/acoustic-space","display_name":"Acoustic space","score":0.46384504437446594},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4622504413127899},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.44319888949394226},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.44091424345970154},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.43918728828430176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39410144090652466},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3682546019554138},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.36498332023620605},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.19829678535461426},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13945218920707703}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.715984582901001},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6858606934547424},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.6662234663963318},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6418414115905762},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.50834721326828},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4840647280216217},{"id":"https://openalex.org/C108250783","wikidata":"https://www.wikidata.org/wiki/Q4674710","display_name":"Acoustic space","level":3,"score":0.46384504437446594},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4622504413127899},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.44319888949394226},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.44091424345970154},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.43918728828430176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39410144090652466},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3682546019554138},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.36498332023620605},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.19829678535461426},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13945218920707703},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/taslp.2017.2690576","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2690576","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:alma.44SUR_INST:11139444080002346","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:HAL:hal-01520194v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01520194","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Audio, Speech and Language Processing, 2017, 25 (6), pp.1266-1277. &#x27E8;10.1109/taslp.2017.2690576&#x27E9;","raw_type":"Journal articles"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/19368","is_oa":false,"landing_page_url":"http://qmro.qmul.ac.uk/xmlui/handle/123456789/19368","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01520194v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01520194","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Audio, Speech and Language Processing, 2017, 25 (6), pp.1266-1277. &#x27E8;10.1109/taslp.2017.2690576&#x27E9;","raw_type":"Journal articles"},"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G3420410296","display_name":"Musical Audio Repurposing using Source Separation","funder_award_id":"EP/L027119/2","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5929590225","display_name":"Musical Audio Repurposing using Source Separation","funder_award_id":"EP/L027119/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5939146501","display_name":"Making Sense of Sounds","funder_award_id":"EP/N014111/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6513227722","display_name":null,"funder_award_id":"EP/L027119/2","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G740539323","display_name":null,"funder_award_id":"EP/L027119/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8995825145","display_name":null,"funder_award_id":"EP/N014111/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W197919343","https://openalex.org/W1503398984","https://openalex.org/W1506806321","https://openalex.org/W1511170870","https://openalex.org/W1650531274","https://openalex.org/W1902027874","https://openalex.org/W1974774036","https://openalex.org/W1984213819","https://openalex.org/W2000911789","https://openalex.org/W2008415856","https://openalex.org/W2049633694","https://openalex.org/W2077159900","https://openalex.org/W2086384421","https://openalex.org/W2096482524","https://openalex.org/W2102381657","https://openalex.org/W2105622288","https://openalex.org/W2105934661","https://openalex.org/W2119110418","https://openalex.org/W2120809168","https://openalex.org/W2123843894","https://openalex.org/W2125838338","https://openalex.org/W2135151673","https://openalex.org/W2137343183","https://openalex.org/W2143959252","https://openalex.org/W2149368536","https://openalex.org/W2232894815","https://openalex.org/W2341412280","https://openalex.org/W2407542046","https://openalex.org/W2408239454","https://openalex.org/W2471278348","https://openalex.org/W2615309413","https://openalex.org/W3129711340","https://openalex.org/W4212863985","https://openalex.org/W4285719527","https://openalex.org/W6675803605","https://openalex.org/W6679714990","https://openalex.org/W6737918430"],"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/W2530685530","https://openalex.org/W2360603947","https://openalex.org/W4375868962","https://openalex.org/W2371528275","https://openalex.org/W2375454309"],"abstract_inverted_index":{"In":[0,50,179],"this":[1],"paper,":[2],"a":[3,35],"system":[4,24,75,183],"for":[5,145,188],"polyphonic":[6,126,192],"sound":[7,42,48,57,80,193],"event":[8,43,81,98,113,194],"detection":[9],"and":[10,19,31,47,141],"tracking":[11,155],"is":[12,32,72,83,102],"proposed,":[13],"based":[14],"on":[15],"spectrogram":[16],"factorization":[17],"techniques":[18],"state":[20],"space":[21],"models.":[22],"The":[23,74],"extends":[25],"probabilistic":[26],"latent":[27,92],"component":[28],"analysis":[29],"(PLCA)":[30],"modeled":[33],"around":[34],"four-dimensional":[36],"spectral":[37],"template":[38],"dictionary":[39],"of":[40,63,110,128,153,162,166,174,191],"frequency,":[41],"class,":[44],"exemplar":[45],"index,":[46],"state.":[49],"order":[51],"to":[52,95,159,171],"jointly":[53],"track":[54],"multiple":[55],"overlapping":[56],"events":[58],"over":[59],"time,":[60],"the":[61,69,78,84,91,96,117,151,172,175,181,189],"integration":[62,152],"linear":[64],"dynamical":[65],"systems":[66],"(LDS)":[67],"within":[68,156],"PLCA":[70,79,157,176],"inference":[71],"proposed.":[73],"assumes":[76],"that":[77,150],"activation":[82],"(noisy)":[85],"observation":[86],"in":[87,164],"an":[88,133,160],"LDS,":[89],"with":[90],"states":[93],"corresponding":[94],"true":[97],"activations.":[99],"LDS":[100,121,154],"training":[101],"achieved":[103],"using":[104,125],"fully":[105],"observed":[106],"data,":[107],"making":[108],"use":[109,173],"ground":[111],"truth-informed":[112],"activations":[114],"produced":[115],"by":[116],"PLCA-based":[118],"model.":[119],"Several":[120],"variants":[122],"are":[123],"evaluated,":[124],"datasets":[127,144],"office":[129],"sounds":[130],"generated":[131],"from":[132],"acoustic":[134],"scene":[135],"simulator,":[136],"as":[137,139,169],"well":[138],"real":[140],"synthesized":[142],"monophonic":[143],"comparative":[146],"purposes.":[147],"Results":[148],"show":[149],"leads":[158],"improvement":[161],"+8.5-10.5%":[163],"terms":[165],"frame-based":[167],"F-measure":[168],"compared":[170],"model":[177],"alone.":[178],"addition,":[180],"proposed":[182],"outperforms":[184],"several":[185],"state-of-the-art":[186],"methods":[187],"task":[190],"detection.":[195]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
