{"id":"https://openalex.org/W2928717951","doi":"https://doi.org/10.1109/icassp.2019.8683627","title":"Sound Event Detection with Sequentially Labelled Data Based on Connectionist Temporal Classification and Unsupervised Clustering","display_name":"Sound Event Detection with Sequentially Labelled Data Based on Connectionist Temporal Classification and Unsupervised Clustering","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2928717951","doi":"https://doi.org/10.1109/icassp.2019.8683627","mag":"2928717951"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683627","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683627","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1904.12102","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063248625","display_name":"Yuanbo Hou","orcid":"https://orcid.org/0000-0001-8469-5740"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuanbo Hou","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, P. R. China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, P. R. China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072482416","display_name":"Qiuqiang Kong","orcid":"https://orcid.org/0000-0003-2864-0475"},"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":"Qiuqiang Kong","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024084275","display_name":"Shengchen Li","orcid":"https://orcid.org/0000-0002-2488-298X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengchen Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, P. R. China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, P. R. China","institution_ids":["https://openalex.org/I139759216"]}]},{"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, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5063248625"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":2.5036,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.89855161,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"46","last_page":"50"},"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":0.9976000189781189,"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":0.9832000136375427,"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":0.7150452136993408},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.6897878050804138},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6631399393081665},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5615440011024475},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5132346153259277},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4883417785167694},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4551016390323639},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.4413028955459595},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42143765091896057}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7150452136993408},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6897878050804138},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6631399393081665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5615440011024475},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5132346153259277},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4883417785167694},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4551016390323639},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.4413028955459595},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42143765091896057},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2019.8683627","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683627","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:alma.44SUR_INST:11139856040002346","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:arXiv.org:1904.12102","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.12102","pdf_url":"https://arxiv.org/pdf/1904.12102","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:epubs.surrey.ac.uk:850807","is_oa":false,"landing_page_url":"http://epubs.surrey.ac.uk/850807/1/Sound%20event%20detection%20-%20AAM.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400680","display_name":"Surrey Research Insight Open Access (The University of Surrey)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28290843","host_organization_name":"University of Surrey","host_organization_lineage":["https://openalex.org/I28290843"],"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 or Workshop Item"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1904.12102","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.12102","pdf_url":"https://arxiv.org/pdf/1904.12102","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[{"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":43,"referenced_works":["https://openalex.org/W317957491","https://openalex.org/W584526652","https://openalex.org/W1522301498","https://openalex.org/W1665214252","https://openalex.org/W1924770834","https://openalex.org/W1977556410","https://openalex.org/W2086384421","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2135131618","https://openalex.org/W2341412280","https://openalex.org/W2354870669","https://openalex.org/W2408239454","https://openalex.org/W2529483679","https://openalex.org/W2566935005","https://openalex.org/W2567070169","https://openalex.org/W2618269622","https://openalex.org/W2763761345","https://openalex.org/W2775505379","https://openalex.org/W2884535146","https://openalex.org/W2901203584","https://openalex.org/W2911648499","https://openalex.org/W2963723765","https://openalex.org/W2963970792","https://openalex.org/W2964121744","https://openalex.org/W3023043375","https://openalex.org/W3103314642","https://openalex.org/W3123940584","https://openalex.org/W4285719527","https://openalex.org/W4289286846","https://openalex.org/W4295723153","https://openalex.org/W6631190155","https://openalex.org/W6637242042","https://openalex.org/W6640212811","https://openalex.org/W6675365184","https://openalex.org/W6731370813","https://openalex.org/W6744964450","https://openalex.org/W6747331233","https://openalex.org/W6752516136","https://openalex.org/W6756850094","https://openalex.org/W6777041185","https://openalex.org/W6788837655","https://openalex.org/W6980901144"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1732468982","https://openalex.org/W1761388607","https://openalex.org/W1997922073","https://openalex.org/W350032239","https://openalex.org/W2604685715","https://openalex.org/W2412160900","https://openalex.org/W2136453575","https://openalex.org/W1596913645"],"abstract_inverted_index":{"Sound":[0],"event":[1],"detection":[2],"(SED)":[3],"methods":[4],"typically":[5],"rely":[6],"on":[7,72,85,97,111,125],"either":[8],"strongly":[9,62,98],"labelled":[10,14,20,63,99,113],"data":[11,21],"or":[12],"weakly":[13,112],"data.":[15],"As":[16],"an":[17],"alternative,":[18],"sequentially":[19],"(SLD)":[22],"was":[23],"proposed.":[24],"In":[25],"SLD,":[26],"the":[27,30,41,80,91,117,120],"events":[28,33,77],"and":[29,101],"order":[31],"of":[32,44,61,75,119,131],"in":[34],"audio":[35],"clips":[36],"are":[37],"known,":[38],"without":[39,127],"knowing":[40],"occurrence":[42],"time":[43,130],"events.":[45,133],"This":[46],"paper":[47],"proposes":[48],"a":[49,66],"connectionist":[50],"temporal":[51],"classification":[52],"(CTC)":[53],"based":[54],"SED":[55,94,108],"system":[56,95,109],"that":[57,79],"uses":[58],"SLD":[59,86,126],"instead":[60],"data,":[64,100,114],"with":[65],"novel":[67],"unsupervised":[68],"clustering":[69],"stage.":[70],"Experiments":[71],"41":[73],"classes":[74],"sound":[76,132],"show":[78],"proposed":[81,121],"two-stage":[82,122],"method":[83,123],"trained":[84,96,110,124],"achieves":[87],"performance":[88],"comparable":[89],"to":[90],"previous":[92],"state-of-the-art":[93,107],"is":[102],"far":[103],"better":[104],"than":[105],"another":[106],"which":[115],"indicates":[116],"effectiveness":[118],"any":[128],"onset/offset":[129]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}