{"id":"https://openalex.org/W2618269622","doi":"https://doi.org/10.1109/icassp.2017.7952704","title":"A first attempt at polyphonic sound event detection using connectionist temporal classification","display_name":"A first attempt at polyphonic sound event detection using connectionist temporal classification","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2618269622","doi":"https://doi.org/10.1109/icassp.2017.7952704","mag":"2618269622"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7952704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100377624","display_name":"Yun Wang","orcid":"https://orcid.org/0000-0002-4749-2984"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun Wang","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":3.3207,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.94423051,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2986","last_page":"2990"},"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":0.9980999827384949,"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":0.9900000095367432,"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":0.7827845811843872},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.659750759601593},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.63538658618927},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6170322895050049},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5480192303657532},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5168314576148987},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.48505181074142456},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.4710645079612732},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.4383350610733032},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4281260073184967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4280101954936981},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42384201288223267},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2821235656738281},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09752801060676575}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7827845811843872},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.659750759601593},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.63538658618927},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6170322895050049},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5480192303657532},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5168314576148987},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.48505181074142456},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.4710645079612732},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4383350610733032},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4281260073184967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4280101954936981},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42384201288223267},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2821235656738281},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09752801060676575},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7952704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W80364729","https://openalex.org/W581956982","https://openalex.org/W1501987291","https://openalex.org/W1533561824","https://openalex.org/W1535031652","https://openalex.org/W1650531274","https://openalex.org/W1972567154","https://openalex.org/W2034215399","https://openalex.org/W2034424181","https://openalex.org/W2043194666","https://openalex.org/W2064675550","https://openalex.org/W2090200552","https://openalex.org/W2090777335","https://openalex.org/W2095705004","https://openalex.org/W2102113734","https://openalex.org/W2123843894","https://openalex.org/W2127141656","https://openalex.org/W2136848157","https://openalex.org/W2327970305","https://openalex.org/W2341412280","https://openalex.org/W2398456099","https://openalex.org/W2398932003","https://openalex.org/W2407005679","https://openalex.org/W2477205648","https://openalex.org/W2566935005","https://openalex.org/W2622742434","https://openalex.org/W2914312680","https://openalex.org/W2963158330","https://openalex.org/W2963211739","https://openalex.org/W2963399116","https://openalex.org/W3098357269","https://openalex.org/W6616837769","https://openalex.org/W6632100227","https://openalex.org/W6632323398","https://openalex.org/W6674330103","https://openalex.org/W6675365184","https://openalex.org/W6712469065","https://openalex.org/W6713457403","https://openalex.org/W6739564277"],"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/W2390487542"],"abstract_inverted_index":{"Sound":[0],"event":[1,33,107],"detection":[2],"is":[3,44,152],"the":[4,8,28,54,58,110,134,141,156],"task":[5],"of":[6,15,53,87,127,140,158,166],"detecting":[7,185],"type,":[9],"starting":[10,49,92],"time,":[11],"and":[12,50,93,138,187],"ending":[13,51,94],"time":[14],"sound":[16,32,55,88,106,113,128,142,159],"events":[17,56,89,114,143,160],"in":[18,57],"audio":[19],"streams.":[20],"Recently,":[21],"recurrent":[22],"neural":[23],"networks":[24],"(RNNs)":[25],"have":[26,191],"become":[27],"mainstream":[29],"solution":[30],"for":[31,105,146],"detection.":[34,108],"Because":[35],"RNNs":[36],"make":[37],"a":[38,73,99,162],"prediction":[39],"at":[40,102],"every":[41],"frame,":[42],"it":[43,81,121],"necessary":[45],"to":[46,83,123,132,154,180,184,195],"provide":[47,84],"exact":[48,91],"times":[52],"training":[59],"data,":[60],"making":[61,120],"data":[62],"annotation":[63],"an":[64],"extremely":[65],"time-consuming":[66],"process.":[67],"Connectionist":[68],"temporal":[69],"classification":[70],"(CTC),":[71],"as":[72,144],"sequence-to-sequence":[74],"model,":[75],"can":[76],"relax":[77],"this":[78],"constraint,":[79],"because":[80],"suffices":[82],"ordered":[85,125],"sequences":[86,126],"without":[90],"times.":[95],"This":[96],"paper":[97],"presents":[98],"first":[100],"attempt":[101],"using":[103],"CTC":[104,151,177],"In":[109],"polyphonic":[111],"situation,":[112],"may":[115],"overlap":[116],"with":[117,170],"each":[118],"other,":[119],"hard":[122],"define":[124],"events.":[129],"We":[130,148],"propose":[131],"use":[133],"boundaries":[135,157],"(i.e.":[136],"starts":[137],"ends)":[139],"tokens":[145],"CTC.":[147],"show":[149],"that":[150],"able":[153],"locate":[155],"on":[161],"very":[163],"noisy":[164],"corpus":[165],"consumer":[167],"generated":[168],"content":[169],"rough":[171],"hints":[172],"about":[173],"their":[174],"positions.":[175],"The":[176],"approach":[178],"seems":[179],"be":[181],"particularly":[182],"suited":[183],"short":[186],"transient":[188],"sounds,":[189],"which":[190],"traditionally":[192],"been":[193],"hardest":[194],"detect.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
