{"id":"https://openalex.org/W2896809327","doi":"https://doi.org/10.1109/icassp.2019.8682278","title":"Connectionist Temporal Localization for Sound Event Detection with Sequential Labeling","display_name":"Connectionist Temporal Localization for Sound Event Detection with Sequential Labeling","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2896809327","doi":"https://doi.org/10.1109/icassp.2019.8682278","mag":"2896809327"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682278","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1810.09052","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100618681","display_name":"Yun Wang","orcid":"https://orcid.org/0000-0003-3117-8955"},"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","[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"]},{"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","[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"]},{"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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00089183,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"745","last_page":"749"},"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":0.9993000030517578,"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":0.9912999868392944,"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/connectionism","display_name":"Connectionism","score":0.8528972268104553},{"id":"https://openalex.org/keywords/ctl*","display_name":"CTL*","score":0.68124920129776},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6688470840454102},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6148914098739624},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.558471143245697},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5023608207702637},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.49369558691978455},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4153589606285095},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39985719323158264},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2309666872024536},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.061001718044281006}],"concepts":[{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.8528972268104553},{"id":"https://openalex.org/C147969180","wikidata":"https://www.wikidata.org/wiki/Q5014579","display_name":"CTL*","level":4,"score":0.68124920129776},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6688470840454102},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6148914098739624},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.558471143245697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5023608207702637},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.49369558691978455},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4153589606285095},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39985719323158264},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2309666872024536},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.061001718044281006},{"id":"https://openalex.org/C154317977","wikidata":"https://www.wikidata.org/wiki/Q376266","display_name":"Cytotoxic T cell","level":3,"score":0.0},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C202751555","wikidata":"https://www.wikidata.org/wiki/Q221681","display_name":"In vitro","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2019.8682278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682278","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:arXiv.org:1810.09052","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.09052","pdf_url":"https://arxiv.org/pdf/1810.09052","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"mag:2896809327","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1810.09052.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1810.09052","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1810.09052","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1810.09052","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.09052","pdf_url":"https://arxiv.org/pdf/1810.09052","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2896809327.pdf","grobid_xml":"https://content.openalex.org/works/W2896809327.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2043701535","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2618269622","https://openalex.org/W2901203584","https://openalex.org/W2963022469","https://openalex.org/W6631190155","https://openalex.org/W6675365184","https://openalex.org/W6749158954","https://openalex.org/W6755644679","https://openalex.org/W6756850094","https://openalex.org/W6884739491"],"related_works":["https://openalex.org/W2280891182","https://openalex.org/W1969022491","https://openalex.org/W2114474724","https://openalex.org/W2984725557","https://openalex.org/W3124216180","https://openalex.org/W2748219818","https://openalex.org/W2952835694","https://openalex.org/W2950025803","https://openalex.org/W2904621594","https://openalex.org/W2945816515","https://openalex.org/W2772992824","https://openalex.org/W3092820804","https://openalex.org/W284021748","https://openalex.org/W3091911211","https://openalex.org/W3127097381","https://openalex.org/W2810962117","https://openalex.org/W3119827015","https://openalex.org/W3094527412","https://openalex.org/W2743691986","https://openalex.org/W2394849137"],"abstract_inverted_index":{"Research":[0],"on":[1,12,87],"sound":[2],"event":[3,24,42],"detection":[4],"(SED)":[5],"with":[6,32,55,129],"weak":[7],"labeling":[8,105,128,131],"has":[9],"mostly":[10],"focused":[11],"presence/absence":[13,130],"labeling,":[14,34,57,108],"which":[15,35,81],"provides":[16],"no":[17],"temporal":[18,38,47,78,115],"information":[19,116],"at":[20],"all":[21],"about":[22],"the":[23,37,41,72,84,100,110,113],"occurrences.":[25],"In":[26],"this":[27],"paper,":[28],"we":[29],"consider":[30],"SED":[31,54],"sequential":[33,56,118,127],"specifies":[36],"order":[39],"of":[40,90,99,112],"boundaries.":[43],"The":[44],"conventional":[45],"connectionist":[46,77],"classification":[48],"(CTC)":[49],"framework,":[50],"when":[51],"applied":[52],"to":[53,65,125],"does":[58],"not":[59],"localize":[60],"long":[61],"events":[62],"well":[63],"due":[64],"a":[66,88,97],"\"peak":[67],"clustering\"":[68],"problem.":[69,85],"We":[70],"adapt":[71],"CTC":[73],"framework":[74],"and":[75,106,132],"propose":[76],"localization":[79],"(CTL),":[80],"successfully":[82],"solves":[83],"Evaluation":[86],"subset":[89],"Audio":[91],"Set":[92],"shows":[93],"that":[94],"CTL":[95,120],"closes":[96],"third":[98],"gap":[101],"between":[102],"presence/":[103],"absence":[104],"strong":[107,133],"demonstrating":[109],"usefulness":[111],"extra":[114],"in":[117],"labeling.":[119,134],"also":[121],"makes":[122],"it":[123],"easy":[124],"combine":[126]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}