{"id":"https://openalex.org/W2065529590","doi":"https://doi.org/10.1109/taslp.2014.2367814","title":"Random Regression Forests for Acoustic Event Detection and Classification","display_name":"Random Regression Forests for Acoustic Event Detection and Classification","publication_year":2014,"publication_date":"2014-11-07","ids":{"openalex":"https://openalex.org/W2065529590","doi":"https://doi.org/10.1109/taslp.2014.2367814","mag":"2065529590"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2014.2367814","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2367814","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058452657","display_name":"Huy Phan","orcid":"https://orcid.org/0000-0003-4096-785X"},"institutions":[{"id":"https://openalex.org/I9341345","display_name":"University of L\u00fcbeck","ror":"https://ror.org/00t3r8h32","country_code":"DE","type":"education","lineage":["https://openalex.org/I9341345"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Huy Phan","raw_affiliation_strings":["Institute for Signal Processing University of L\u00fcbeck, University of L\u00fcbeck, L\u00fcbeck, Germany","The Institute for Signal Processing and the Graduate School for Computing in Medicine and Life Sciences, University of L\u00fcbeck, L\u00fcbeck, Germany#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Signal Processing University of L\u00fcbeck, University of L\u00fcbeck, L\u00fcbeck, Germany","institution_ids":["https://openalex.org/I9341345"]},{"raw_affiliation_string":"The Institute for Signal Processing and the Graduate School for Computing in Medicine and Life Sciences, University of L\u00fcbeck, L\u00fcbeck, Germany#TAB#","institution_ids":["https://openalex.org/I9341345"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110996796","display_name":"Marco Maas","orcid":null},"institutions":[{"id":"https://openalex.org/I9341345","display_name":"University of L\u00fcbeck","ror":"https://ror.org/00t3r8h32","country_code":"DE","type":"education","lineage":["https://openalex.org/I9341345"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marco Maas","raw_affiliation_strings":["The Institute for Signal Processing and the Graduate School for Computing in Medicine and Life Sciences, University of L\u00fcbeck, L\u00fcbeck, Germany#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Institute for Signal Processing and the Graduate School for Computing in Medicine and Life Sciences, University of L\u00fcbeck, L\u00fcbeck, Germany#TAB#","institution_ids":["https://openalex.org/I9341345"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074089177","display_name":"Radoslaw Mazur","orcid":null},"institutions":[{"id":"https://openalex.org/I9341345","display_name":"University of L\u00fcbeck","ror":"https://ror.org/00t3r8h32","country_code":"DE","type":"education","lineage":["https://openalex.org/I9341345"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Radoslaw Mazur","raw_affiliation_strings":["Institute for Signal Processing, University of L\u00fcbeck, L\u00fcbeck, Germany","The Institute for Signal Processing, University of L\u00fcbeck, L\u00fcbeck, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Signal Processing, University of L\u00fcbeck, L\u00fcbeck, Germany","institution_ids":["https://openalex.org/I9341345"]},{"raw_affiliation_string":"The Institute for Signal Processing, University of L\u00fcbeck, L\u00fcbeck, Germany","institution_ids":["https://openalex.org/I9341345"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063948113","display_name":"Alfred Mertins","orcid":"https://orcid.org/0000-0001-5718-577X"},"institutions":[{"id":"https://openalex.org/I9341345","display_name":"University of L\u00fcbeck","ror":"https://ror.org/00t3r8h32","country_code":"DE","type":"education","lineage":["https://openalex.org/I9341345"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alfred Mertins","raw_affiliation_strings":["Institute for Signal Processing, University of L\u00fcbeck, L\u00fcbeck, Germany","The Institute for Signal Processing, University of L\u00fcbeck, L\u00fcbeck, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Signal Processing, University of L\u00fcbeck, L\u00fcbeck, Germany","institution_ids":["https://openalex.org/I9341345"]},{"raw_affiliation_string":"The Institute for Signal Processing, University of L\u00fcbeck, L\u00fcbeck, Germany","institution_ids":["https://openalex.org/I9341345"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":15.2247,"has_fulltext":false,"cited_by_count":109,"citation_normalized_percentile":{"value":0.99048837,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"23","issue":"1","first_page":"20","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.6833759546279907},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6788076162338257},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6688846945762634},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.5908117294311523},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5546292662620544},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"Regression analysis","score":0.45421090722084045},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.4480474889278412},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4426485002040863},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3715888261795044},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3673321306705475},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.19208604097366333},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17203429341316223}],"concepts":[{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.6833759546279907},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6788076162338257},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6688846945762634},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.5908117294311523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5546292662620544},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.45421090722084045},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.4480474889278412},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4426485002040863},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3715888261795044},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3673321306705475},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.19208604097366333},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17203429341316223},{"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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/taslp.2014.2367814","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2367814","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:kar.kent.ac.uk:72691","is_oa":false,"landing_page_url":"https://doi.org/10.1109/TASLP.2014.2367814>)","pdf_url":null,"source":{"id":"https://openalex.org/S4377196264","display_name":"Kent Academic Repository (University of Kent)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20581793","host_organization_name":"University of Kent","host_organization_lineage":["https://openalex.org/I20581793"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.707.8145","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.707.8145","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.isip.uni-luebeck.de/fileadmin/uploads/tx_wapublications/phan2015_02.pdf","raw_type":"text"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/65049","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/65049","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":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W85133398","https://openalex.org/W172871939","https://openalex.org/W206961783","https://openalex.org/W795299307","https://openalex.org/W1533561824","https://openalex.org/W1622490909","https://openalex.org/W1837649128","https://openalex.org/W1964357740","https://openalex.org/W1964498219","https://openalex.org/W2005122913","https://openalex.org/W2009504845","https://openalex.org/W2021096090","https://openalex.org/W2046972719","https://openalex.org/W2056132907","https://openalex.org/W2064543148","https://openalex.org/W2065698093","https://openalex.org/W2074764925","https://openalex.org/W2077159900","https://openalex.org/W2092216166","https://openalex.org/W2102381657","https://openalex.org/W2103958600","https://openalex.org/W2105068979","https://openalex.org/W2108815700","https://openalex.org/W2115447976","https://openalex.org/W2124911490","https://openalex.org/W2125337786","https://openalex.org/W2125838338","https://openalex.org/W2129634963","https://openalex.org/W2134426937","https://openalex.org/W2135131618","https://openalex.org/W2158762315","https://openalex.org/W2163123273","https://openalex.org/W2165880886","https://openalex.org/W2171680721","https://openalex.org/W2186582651","https://openalex.org/W2229530802","https://openalex.org/W2294701319","https://openalex.org/W2327970305","https://openalex.org/W2403485243","https://openalex.org/W2911964244","https://openalex.org/W2963922351","https://openalex.org/W3215500402","https://openalex.org/W6632323398","https://openalex.org/W6639003370","https://openalex.org/W6675598773","https://openalex.org/W6678439021","https://openalex.org/W6680350228","https://openalex.org/W6683181420","https://openalex.org/W6696804643","https://openalex.org/W6713518917"],"related_works":["https://openalex.org/W2048488252","https://openalex.org/W4289884158","https://openalex.org/W4288365262","https://openalex.org/W2940614149","https://openalex.org/W2787485953","https://openalex.org/W3217432596","https://openalex.org/W4289356671","https://openalex.org/W2389155397","https://openalex.org/W2165884543","https://openalex.org/W2312753042"],"abstract_inverted_index":{"Despite":[0],"the":[1,4,17,34,38,78,90,99,105,119,126,131,135,141,151,163,169,189,199,204],"success":[2],"of":[3,19,32,104,134,140,203],"automatic":[5],"speech":[6,44],"recognition":[7,157],"framework":[8],"in":[9,25,43,65],"its":[10,14],"own":[11],"application":[12],"field,":[13],"adaptation":[15],"to":[16,37,98,150,161,167],"problem":[18,35,186],"acoustic":[20],"event":[21,63,92,110,147,170,174,179],"detection":[22,180],"has":[23],"resulted":[24],"limited":[26],"success.":[27],"In":[28],"this":[29],"paper,":[30],"instead":[31],"treating":[33],"similar":[36],"segmentation":[39],"and":[40,53,95,102,137,166,181,196,201],"classification":[41],"tasks":[42],"recognition,":[45],"we":[46],"pose":[47],"it":[48],"as":[49,71,183],"a":[50,72,108,112,155,184],"regression":[51,114,153,185],"task":[52],"propose":[54],"an":[55,123],"approach":[56],"based":[57],"on":[58,192],"random":[59],"forest":[60],"regression.":[61],"Furthermore,":[62],"localization":[64,182],"time":[66],"can":[67],"be":[68],"efficiently":[69],"handled":[70],"joint":[73],"problem.":[74],"We":[75],"first":[76],"decompose":[77],"training":[79],"audio":[80],"signals":[81],"into":[82,172],"multiple":[83,146],"interleaved":[84],"superframes":[85,165,171],"which":[86],"are":[87],"annotated":[88],"with":[89,145],"corresponding":[91],"class":[93],"labels":[94],"their":[96],"displacements":[97],"temporal":[100],"onsets":[101],"offsets":[103],"events.":[106,142],"For":[107],"specific":[109],"category,":[111],"random-forest":[113],"model":[115],"is":[116,159,187],"learned":[117,127],"using":[118],"displacement":[120],"information.":[121],"Given":[122],"unseen":[124],"superframe,":[125],"regressor":[128],"will":[129],"output":[130],"continuous":[132],"estimates":[133],"onset":[136],"offset":[138],"locations":[139],"To":[143],"deal":[144],"categories,":[148],"prior":[149],"category-specific":[152],"phase,":[154],"superframe-wise":[156],"phase":[158],"performed":[160],"reject":[162],"background":[164],"classify":[168],"different":[173],"categories.":[175],"While":[176],"jointly":[177],"posing":[178],"novel,":[188],"superior":[190],"performance":[191],"two":[193],"databases":[194],"ITC-Irst":[195],"UPC-TALP":[197],"demonstrates":[198],"efficiency":[200],"potential":[202],"proposed":[205],"approach.":[206]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":21},{"year":2017,"cited_by_count":18},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":8}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}