{"id":"https://openalex.org/W3161272933","doi":"https://doi.org/10.1109/icassp39728.2021.9414450","title":"Self-Training for Sound Event Detection in Audio Mixtures","display_name":"Self-Training for Sound Event Detection in Audio Mixtures","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161272933","doi":"https://doi.org/10.1109/icassp39728.2021.9414450","mag":"3161272933"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414450","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100750094","display_name":"Sangwook Park","orcid":"https://orcid.org/0000-0002-6817-4846"},"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":"Sangwook Park","raw_affiliation_strings":["Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114142044","display_name":"Ashwin Bellur","orcid":null},"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":"Ashwin Bellur","raw_affiliation_strings":["Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102000970","display_name":"David K. Han","orcid":"https://orcid.org/0000-0001-5055-5408"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David K. Han","raw_affiliation_strings":["Drexel University,Department of Electrical and Computer Engineering,Philadelphia,PA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Drexel University,Department of Electrical and Computer Engineering,Philadelphia,PA,USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038788686","display_name":"Mounya Elhilali","orcid":"https://orcid.org/0000-0003-2597-738X"},"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":"Mounya Elhilali","raw_affiliation_strings":["Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5442,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.82894825,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"341","last_page":"345"},"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":0.9991999864578247,"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":0.9923999905586243,"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/timestamp","display_name":"Timestamp","score":0.7908502221107483},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7852125763893127},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7324612140655518},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5010490417480469},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4984557628631592},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4976096451282501},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4890364110469818},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4479309618473053},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44506335258483887},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4323018789291382},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4299365282058716},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3431583642959595},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32768237590789795},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2537970542907715},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.1182946264743805},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.11627507209777832}],"concepts":[{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.7908502221107483},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7852125763893127},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7324612140655518},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5010490417480469},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4984557628631592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4976096451282501},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4890364110469818},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4479309618473053},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44506335258483887},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4323018789291382},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4299365282058716},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3431583642959595},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32768237590789795},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2537970542907715},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.1182946264743805},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.11627507209777832},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/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/icassp39728.2021.9414450","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1654482605","https://openalex.org/W2408239454","https://openalex.org/W2591013610","https://openalex.org/W2592691248","https://openalex.org/W2810417023","https://openalex.org/W2897282582","https://openalex.org/W2938357656","https://openalex.org/W2950746339","https://openalex.org/W2953070460","https://openalex.org/W2959539607","https://openalex.org/W2963216549","https://openalex.org/W2963956526","https://openalex.org/W2984353870","https://openalex.org/W3015805515","https://openalex.org/W3049446265","https://openalex.org/W3109837239","https://openalex.org/W3121328487","https://openalex.org/W3136198447","https://openalex.org/W3160339728","https://openalex.org/W6731965104","https://openalex.org/W6733814495","https://openalex.org/W6755947350","https://openalex.org/W6761626979","https://openalex.org/W6765710459","https://openalex.org/W6768954131","https://openalex.org/W6780411803","https://openalex.org/W6791883635","https://openalex.org/W6795095373"],"related_works":["https://openalex.org/W4287205925","https://openalex.org/W3161658874","https://openalex.org/W2289868279","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W2769884427","https://openalex.org/W2088690926","https://openalex.org/W2157165686"],"abstract_inverted_index":{"Sound":[0],"event":[1,123],"detection":[2,124],"(SED)":[3],"takes":[4],"on":[5],"the":[6,49,105,126,129,139,153],"task":[7],"of":[8,11,44,51,74,128],"identifying":[9],"presence":[10],"specific":[12],"sound":[13,62,122,158],"events":[14],"in":[15,24,35,42,72,87,125,151],"a":[16,80,97,101,135],"complex":[17],"audio":[18,31],"recording.":[19],"SED":[20,45],"has":[21],"tremendous":[22],"implications":[23],"video":[25],"analytics,":[26],"smart":[27],"speaker":[28],"algorithms":[29],"and":[30,65,108,133],"tagging.":[32],"Recent":[33],"advances":[34,41],"deep":[36],"learning":[37,89],"have":[38],"afforded":[39],"remarkable":[40],"performance":[43],"systems;":[46],"albeit":[47],"at":[48],"cost":[50],"extensive":[52],"labeling":[53],"efforts":[54],"to":[55,69,83,121],"train":[56],"supervised":[57,88],"methods":[58],"using":[59,90],"fully":[60],"described":[61],"class":[63],"labels":[64,107],"timestamps.":[66],"In":[67],"order":[68],"address":[70],"limitations":[71],"availability":[73],"training":[75,117],"data,":[76],"this":[77,143],"work":[78],"proposes":[79,96],"self-training":[81,146],"technique":[82,118],"leverage":[84],"unlabeled":[85],"datasets":[86],"pseudo":[91,112],"label":[92],"estimation.":[93],"This":[94],"approach":[95,147],"dual-term":[98],"objective":[99],"function:":[100],"classification":[102],"loss":[103,110],"for":[104,111,142],"original":[106],"expectation":[109],"labels.":[113],"The":[114,145],"proposed":[115],"self":[116],"is":[119,148],"applied":[120],"context":[127],"DCASE":[130],"2020":[131],"challenge,":[132],"reports":[134],"notable":[136],"improvement":[137],"over":[138],"baseline":[140],"system":[141],"task.":[144],"particularly":[149],"effective":[150],"extending":[152],"labeled":[154],"database":[155],"with":[156],"concurrent":[157],"events.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}