{"id":"https://openalex.org/W3016195076","doi":"https://doi.org/10.1109/icassp40776.2020.9053609","title":"Weakly-Supervised Sound Event Detection with Self-Attention","display_name":"Weakly-Supervised Sound Event Detection with Self-Attention","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016195076","doi":"https://doi.org/10.1109/icassp40776.2020.9053609","mag":"3016195076"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053609","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5103146872","display_name":"Koichi Miyazaki","orcid":"https://orcid.org/0000-0003-0196-5624"},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koichi Miyazaki","raw_affiliation_strings":["LINE Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LINE Corporation, Japan","institution_ids":["https://openalex.org/I4210096607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113730169","display_name":"Tatsuya Komatsu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Komatsu","raw_affiliation_strings":["LINE Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LINE Corporation, Japan","institution_ids":["https://openalex.org/I4210096607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078778981","display_name":"Tomoki Hayashi","orcid":"https://orcid.org/0000-0001-8782-4093"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Hayashi","raw_affiliation_strings":["Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042118446","display_name":"Kazuya Takeda","orcid":"https://orcid.org/0000-0002-0330-1787"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuya Takeda","raw_affiliation_strings":["Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":73,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"66","last_page":"70"},"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":0.9878000020980835,"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":0.9793999791145325,"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":0.8170572519302368},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6561034917831421},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5941771864891052},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5881634950637817},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5501506924629211},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5274591445922852},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.5065509080886841},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4918804168701172},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43525534868240356},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3874490261077881},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3701382279396057},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3638574481010437},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.10665944218635559},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.10052692890167236},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08341774344444275}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8170572519302368},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6561034917831421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5941771864891052},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5881634950637817},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5501506924629211},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5274591445922852},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.5065509080886841},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4918804168701172},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43525534868240356},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3874490261077881},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3701382279396057},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3638574481010437},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.10665944218635559},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.10052692890167236},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08341774344444275},{"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053609","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1994488211","https://openalex.org/W2009504845","https://openalex.org/W2010792435","https://openalex.org/W2118230268","https://openalex.org/W2133564696","https://openalex.org/W2135342008","https://openalex.org/W2342547278","https://openalex.org/W2354870669","https://openalex.org/W2398030828","https://openalex.org/W2408239454","https://openalex.org/W2509065397","https://openalex.org/W2591013610","https://openalex.org/W2592691248","https://openalex.org/W2746554716","https://openalex.org/W2770119437","https://openalex.org/W2785934082","https://openalex.org/W2798158991","https://openalex.org/W2799258971","https://openalex.org/W2889519245","https://openalex.org/W2892009249","https://openalex.org/W2892140764","https://openalex.org/W2896457183","https://openalex.org/W2953070460","https://openalex.org/W2959539607","https://openalex.org/W2962780374","https://openalex.org/W2963099423","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963543871","https://openalex.org/W2963610932","https://openalex.org/W2963807318","https://openalex.org/W2964308564","https://openalex.org/W2972818416","https://openalex.org/W3007328579","https://openalex.org/W3008357631","https://openalex.org/W3036237438","https://openalex.org/W3098357269","https://openalex.org/W3103314642","https://openalex.org/W3123940584","https://openalex.org/W4385245566","https://openalex.org/W6679434410","https://openalex.org/W6704490260","https://openalex.org/W6712242886","https://openalex.org/W6733814495","https://openalex.org/W6739901393","https://openalex.org/W6746278845","https://openalex.org/W6747701563","https://openalex.org/W6754299077","https://openalex.org/W6754925833","https://openalex.org/W6755207826","https://openalex.org/W6779574021","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4304700937","https://openalex.org/W2996851014","https://openalex.org/W4387885913","https://openalex.org/W2808647726","https://openalex.org/W4384644158","https://openalex.org/W1528789570","https://openalex.org/W2787518671","https://openalex.org/W3110732717"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,101],"propose":[4],"a":[5,14,21,72],"novel":[6],"sound":[7],"event":[8],"detection":[9],"(SED)":[10],"method":[11,27,70,118],"that":[12,115],"incorporates":[13],"self-attention":[15,36,136],"mechanism":[16,137],"of":[17,34,47,60,88,97],"the":[18,29,48,57,63,68,77,86,89,95,98,103,107,116,120,129,135],"Transformer":[19,30],"for":[20,80,140],"weakly-supervised":[22],"learning":[23],"scenario.":[24],"The":[25,111],"proposed":[26,69,99,117],"utilizes":[28],"encoder,":[31],"which":[32,84,125],"consists":[33],"multiple":[35],"modules,":[37],"allowing":[38],"to":[39],"take":[40],"both":[41],"local":[42],"and":[43,134],"global":[44],"context":[45],"information":[46],"input":[49,78],"feature":[50],"sequence":[51,79,91],"into":[52,76],"account.":[53],"Furthermore,":[54],"inspired":[55],"by":[56],"great":[58],"success":[59],"BERT":[61],"in":[62],"natural":[64],"language":[65],"processing":[66],"field,":[67],"introduces":[71],"special":[73],"tag":[74],"token":[75],"weak":[81],"label":[82],"prediction,":[83],"enables":[85],"aggregation":[87],"whole":[90],"information.":[92],"To":[93],"demonstrate":[94,114],"performance":[96],"method,":[100,124],"conduct":[102],"experimental":[104,112],"evaluation":[105],"using":[106],"DCASE2019":[108,121],"Task4":[109,122],"dataset.":[110],"results":[113],"outperforms":[119],"baseline":[123],"is":[126],"based":[127],"on":[128],"convolutional":[130],"recurrent":[131],"neural":[132],"network,":[133],"effectively":[138],"works":[139],"SED.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}