{"id":"https://openalex.org/W3012237858","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023025","title":"Augmented Strategy For Polyphonic Sound Event Detection","display_name":"Augmented Strategy For Polyphonic Sound Event Detection","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3012237858","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023025","mag":"3012237858"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5101511925","display_name":"Bolun Wang","orcid":"https://orcid.org/0000-0002-0963-3942"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bolun Wang","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036394527","display_name":"Zhonghua Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong-Hua Fu","raw_affiliation_strings":["Xi'an IFLYTEK Hyper Brain Information Technology Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Xi'an IFLYTEK Hyper Brain Information Technology Co., Ltd","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100448241","display_name":"Hao Wu","orcid":"https://orcid.org/0000-0001-8839-6123"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Wu","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101511925"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.1659,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.49484473,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"6","issue":null,"first_page":"1496","last_page":"1500"},"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":0.9962999820709229,"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":0.9948999881744385,"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":0.806368350982666},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.7164879441261292},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.61892169713974},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5489566326141357},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5286693572998047},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4869180917739868},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44288167357444763},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4127809405326843},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35297638177871704},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3220129609107971}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.806368350982666},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.7164879441261292},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.61892169713974},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5489566326141357},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5286693572998047},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4869180917739868},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44288167357444763},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4127809405326843},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35297638177871704},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3220129609107971},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":21,"referenced_works":["https://openalex.org/W1512460134","https://openalex.org/W1533561824","https://openalex.org/W1650531274","https://openalex.org/W2034215399","https://openalex.org/W2086384421","https://openalex.org/W2089368853","https://openalex.org/W2090200552","https://openalex.org/W2116681922","https://openalex.org/W2119110418","https://openalex.org/W2126109423","https://openalex.org/W2137561966","https://openalex.org/W2160860215","https://openalex.org/W2341412280","https://openalex.org/W2408239454","https://openalex.org/W2775794021","https://openalex.org/W4288375019","https://openalex.org/W4289329167","https://openalex.org/W6630793456","https://openalex.org/W6632323398","https://openalex.org/W6636898527","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/W4385572368"],"abstract_inverted_index":{"Sound":[0],"event":[1,33,59,63,138],"detection":[2,54],"is":[3,130],"an":[4,71],"important":[5],"issue":[6],"for":[7,74],"many":[8],"applications":[9],"like":[10],"audio":[11],"content":[12],"retrieval,":[13],"intelligent":[14],"monitoring,":[15],"and":[16,45,86,113,115,135,139],"scene-based":[17],"interaction.":[18],"The":[19,125],"traditional":[20],"studies":[21],"on":[22,28,56,132],"this":[23,67,75],"topic":[24],"are":[25,142],"mainly":[26],"focusing":[27],"identification":[29],"of":[30,80,84,122,127],"single":[31],"sound":[32,40,58],"class.":[34],"However,":[35],"in":[36],"real":[37],"applications,":[38],"several":[39],"events":[41],"usually":[42],"happen":[43],"concurrently":[44],"with":[46,62],"different":[47,123],"durations.":[48],"That":[49],"leads":[50],"to":[51,97,101,118],"a":[52,81,105],"new":[53,106],"task":[55],"polyphonic":[57],"classification":[60],"along":[61],"time":[64],"boundaries.":[65],"In":[66],"paper,":[68],"we":[69],"propose":[70],"augmented":[72],"strategy":[73,93,129],"task,":[76],"which":[77],"faces":[78],"challenges":[79],"large":[82],"amount":[83],"unbalanced":[85],"weakly":[87],"labelled":[88],"training":[89,99],"data.":[90],"Specifically,":[91],"the":[92,120,128,137,146],"includes":[94],"data":[95,103],"augmentation":[96],"enrich":[98],"set":[100],"eliminate":[102],"unbalance,":[104],"loss":[107],"function":[108],"that":[109],"combines":[110],"cross":[111],"entropy":[112],"F-score,":[114],"model":[116],"fusion":[117],"integrate":[119],"powers":[121],"classifiers.":[124],"performance":[126],"validated":[131],"DCASE2019":[133],"dataset,":[134],"both":[136],"segment":[140],"detections":[141],"significantly":[143],"improved":[144],"over":[145],"baseline":[147],"system.":[148]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}