{"id":"https://openalex.org/W2937959246","doi":"https://doi.org/10.1109/icassp.2019.8682858","title":"Sound Event Envelope Estimation in Polyphonic Mixtures","display_name":"Sound Event Envelope Estimation in Polyphonic Mixtures","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2937959246","doi":"https://doi.org/10.1109/icassp.2019.8682858","mag":"2937959246"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5041615273","display_name":"Irene Mart\u00edn-Morat\u00f3","orcid":"https://orcid.org/0000-0002-2115-0193"},"institutions":[{"id":"https://openalex.org/I16097986","display_name":"Universitat de Val\u00e8ncia","ror":"https://ror.org/043nxc105","country_code":"ES","type":"education","lineage":["https://openalex.org/I16097986"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Irene Martin-Morato","raw_affiliation_strings":["Department of Computer Science, Universitat de Val\u00e8ncia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Universitat de Val\u00e8ncia","institution_ids":["https://openalex.org/I16097986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079981416","display_name":"Annamaria Mesaros","orcid":"https://orcid.org/0000-0002-6640-9752"},"institutions":[{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI","US"],"is_corresponding":false,"raw_author_name":"Annamaria Mesaros","raw_affiliation_strings":["Laboratory of Signal Processing, Tampere University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Signal Processing, Tampere University of Technology","institution_ids":["https://openalex.org/I4210121626","https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059929826","display_name":"Toni Heittola","orcid":"https://orcid.org/0000-0002-8855-0415"},"institutions":[{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI","US"],"is_corresponding":false,"raw_author_name":"Toni Heittola","raw_affiliation_strings":["Laboratory of Signal Processing, Tampere University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Signal Processing, Tampere University of Technology","institution_ids":["https://openalex.org/I4210121626","https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049691461","display_name":"Tuomas Virtanen","orcid":"https://orcid.org/0000-0002-4604-9729"},"institutions":[{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI","US"],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":["Laboratory of Signal Processing, Tampere University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Signal Processing, Tampere University of Technology","institution_ids":["https://openalex.org/I4210121626","https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089104482","display_name":"M\u00e1ximo Cobos","orcid":"https://orcid.org/0000-0001-7318-3192"},"institutions":[{"id":"https://openalex.org/I16097986","display_name":"Universitat de Val\u00e8ncia","ror":"https://ror.org/043nxc105","country_code":"ES","type":"education","lineage":["https://openalex.org/I16097986"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Maximo Cobos","raw_affiliation_strings":["Department of Computer Science, Universitat de Val\u00e8ncia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Universitat de Val\u00e8ncia","institution_ids":["https://openalex.org/I16097986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067408837","display_name":"Francesc J. Ferri","orcid":"https://orcid.org/0000-0002-1543-3568"},"institutions":[{"id":"https://openalex.org/I16097986","display_name":"Universitat de Val\u00e8ncia","ror":"https://ror.org/043nxc105","country_code":"ES","type":"education","lineage":["https://openalex.org/I16097986"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Francesc J. Ferri","raw_affiliation_strings":["Department of Computer Science, Universitat de Val\u00e8ncia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Universitat de Val\u00e8ncia","institution_ids":["https://openalex.org/I16097986"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1683,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.78513604,"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":"935","last_page":"939"},"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":0.9990000128746033,"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":0.9965000152587891,"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/polyphony","display_name":"Polyphony","score":0.8002678155899048},{"id":"https://openalex.org/keywords/envelope","display_name":"Envelope (radar)","score":0.7756693363189697},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.7277052998542786},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6796589493751526},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6276276111602783},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6143815517425537},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5841898918151855},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5181987881660461},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4710139036178589},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.4335387945175171},{"id":"https://openalex.org/keywords/amplitude","display_name":"Amplitude","score":0.4308532178401947},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.42948147654533386},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41185638308525085},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4107872247695923},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3415522575378418},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16869905591011047},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1195020079612732},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.09567850828170776},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07218095660209656}],"concepts":[{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.8002678155899048},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.7756693363189697},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.7277052998542786},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6796589493751526},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6276276111602783},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6143815517425537},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5841898918151855},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5181987881660461},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4710139036178589},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.4335387945175171},{"id":"https://openalex.org/C180205008","wikidata":"https://www.wikidata.org/wiki/Q159190","display_name":"Amplitude","level":2,"score":0.4308532178401947},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.42948147654533386},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41185638308525085},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4107872247695923},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3415522575378418},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16869905591011047},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1195020079612732},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.09567850828170776},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07218095660209656},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"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/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2019.8682858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:trepo.tuni.fi:10024/215366","is_oa":false,"landing_page_url":"https://trepo.tuni.fi/handle/10024/215366","pdf_url":null,"source":{"id":"https://openalex.org/S7407055260","display_name":"Trepo - Institutional Repository of Tampere University","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2038484192","https://openalex.org/W2408239454","https://openalex.org/W2758665125","https://openalex.org/W2771361008","https://openalex.org/W2775505379","https://openalex.org/W2775794021","https://openalex.org/W2884011836","https://openalex.org/W2889495646","https://openalex.org/W2963099423","https://openalex.org/W2964121744","https://openalex.org/W4289329167","https://openalex.org/W6631190155","https://openalex.org/W6747331233","https://openalex.org/W6753516609"],"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/W2375454309","https://openalex.org/W2374135200","https://openalex.org/W1997162386"],"abstract_inverted_index":{"Sound":[0],"event":[1,48,90,128],"detection":[2,144],"is":[3,49,119],"the":[4,9,23,33,37,62,66,69,84,99,103,133,140],"task":[5],"of":[6,14,68,76,87,102,139],"identifying":[7],"automatically":[8],"presence":[10],"and":[11,64,126],"temporal":[12],"boundaries":[13],"sound":[15,89,127],"events":[16],"within":[17],"an":[18,47],"input":[19],"audio":[20],"stream.":[21],"In":[22],"last":[24],"years,":[25],"deep":[26],"learning":[27],"methods":[28],"have":[29],"established":[30],"themselves":[31],"as":[32],"state-of-the-art":[34],"approach":[35],"for":[36,111],"task,":[38],"using":[39],"binary":[40,55],"indicators":[41,57],"during":[42],"training":[43],"to":[44,82,122,147],"denote":[45],"whether":[46],"active":[50],"or":[51],"inactive.":[52],"However,":[53],"such":[54],"activity":[56],"do":[58],"not":[59],"fully":[60],"describe":[61],"events,":[63],"estimating":[65],"envelope":[67,124,134],"sounds":[70,141],"could":[71],"provide":[72],"more":[73],"precise":[74],"modeling":[75,138],"their":[77,114],"activity.":[78],"This":[79],"paper":[80],"proposes":[81],"estimate":[83],"amplitude":[85,100],"envelopes":[86,101],"target":[88,104],"classes":[91],"in":[92],"polyphonic":[93],"mixtures.":[94],"For":[95],"training,":[96],"we":[97],"use":[98],"sounds,":[105],"calculated":[106],"from":[107,113],"mixture":[108],"signals":[109],"and,":[110],"comparison,":[112],"isolated":[115],"counterparts.":[116],"The":[117],"model":[118],"then":[120],"used":[121],"perform":[123],"estimation":[125,135],"detection.":[129],"Results":[130],"show":[131],"that":[132],"allows":[136],"good":[137],"activity,":[142],"with":[143],"results":[145],"comparable":[146],"current":[148],"state-of-the":[149],"art.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}