{"id":"https://openalex.org/W4372260505","doi":"https://doi.org/10.1109/icassp49357.2023.10095687","title":"Semi-Supervised Sound Event Detection with Pre-Trained Model","display_name":"Semi-Supervised Sound Event Detection with Pre-Trained Model","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260505","doi":"https://doi.org/10.1109/icassp49357.2023.10095687"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5010216533","display_name":"Liang Xu","orcid":"https://orcid.org/0000-0001-5746-4111"},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]},{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liang Xu","raw_affiliation_strings":["Beijing Institute of Technology,School of Information and Electronics,Beijing,China","Samsung Research China-Beijing (SRC-B), Beijing, China","School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Information and Electronics,Beijing,China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Samsung Research China-Beijing (SRC-B), Beijing, China","institution_ids":["https://openalex.org/I4210155230"]},{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101635936","display_name":"Lizhong Wang","orcid":"https://orcid.org/0000-0002-2654-5178"},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lizhong Wang","raw_affiliation_strings":["Samsung Research China-Beijing (SRC-B),Beijing,China","Samsung Research China-Beijing (SRC-B), Beijing, China"],"affiliations":[{"raw_affiliation_string":"Samsung Research China-Beijing (SRC-B),Beijing,China","institution_ids":["https://openalex.org/I4210155230"]},{"raw_affiliation_string":"Samsung Research China-Beijing (SRC-B), Beijing, China","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091725071","display_name":"Sijun Bi","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sijun Bi","raw_affiliation_strings":["Beijing Institute of Technology,School of Information and Electronics,Beijing,China","School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Information and Electronics,Beijing,China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041853771","display_name":"Hanyue Liu","orcid":"https://orcid.org/0000-0001-8357-6010"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanyue Liu","raw_affiliation_strings":["Beijing Institute of Technology,School of Information and Electronics,Beijing,China","School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Information and Electronics,Beijing,China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100378497","display_name":"Jing Wang","orcid":"https://orcid.org/0000-0002-3653-9951"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Wang","raw_affiliation_strings":["Beijing Institute of Technology,School of Information and Electronics,Beijing,China","School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Information and Electronics,Beijing,China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5010216533"],"corresponding_institution_ids":["https://openalex.org/I125839683","https://openalex.org/I4210155230"],"apc_list":null,"apc_paid":null,"fwci":4.0953,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.95035549,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983000159263611,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9860000014305115,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7868521213531494},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6298739910125732},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5949525833129883},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.573810875415802},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.563726544380188},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5215377807617188},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4439551830291748},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.43771976232528687},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37563356757164},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3693235218524933}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7868521213531494},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6298739910125732},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5949525833129883},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.573810875415802},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.563726544380188},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5215377807617188},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4439551830291748},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.43771976232528687},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37563356757164},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3693235218524933},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2408239454","https://openalex.org/W2593116425","https://openalex.org/W2922509574","https://openalex.org/W2936774411","https://openalex.org/W2951970475","https://openalex.org/W2953070460","https://openalex.org/W2963099423","https://openalex.org/W2963723765","https://openalex.org/W3016195076","https://openalex.org/W3036601975","https://openalex.org/W3094550259","https://openalex.org/W3162400960","https://openalex.org/W3196645599","https://openalex.org/W3196974791","https://openalex.org/W3198165172","https://openalex.org/W3198860978","https://openalex.org/W3201143670","https://openalex.org/W3203468141","https://openalex.org/W3205267198","https://openalex.org/W3205475937","https://openalex.org/W4221149441","https://openalex.org/W4225312629","https://openalex.org/W4225706374","https://openalex.org/W4289329167","https://openalex.org/W6733814495","https://openalex.org/W6753516609","https://openalex.org/W6764051988","https://openalex.org/W6780218876","https://openalex.org/W6802510933","https://openalex.org/W6810303655"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W3184123547","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861","https://openalex.org/W2488941600"],"abstract_inverted_index":{"Sound":[0],"event":[1,138],"detection":[2,45,170],"(SED)":[3],"is":[4,73,101],"an":[5],"interesting":[6],"but":[7],"challenging":[8],"task":[9,105],"due":[10],"to":[11,40,110,131],"the":[12,29,44,57,70,78,83,88,92,112,133,141,154],"scarcity":[13],"of":[14,59,167],"data":[15],"and":[16,33,75,106,116,140,158],"diverse":[17],"sound":[18,169],"events":[19],"in":[20,42,53,56,91,160,165],"real":[21],"life.":[22],"In":[23,120],"this":[24],"paper,":[25],"we":[26,122],"focus":[27],"on":[28],"semi-supervised":[30],"SED":[31,104],"task,":[32],"combine":[34],"pre-trained":[35,84,97,150],"model":[36,85,98,151],"from":[37,114],"other":[38],"field":[39,58],"assist":[41],"improving":[43],"effect.":[46],"Pre-trained":[47],"models":[48],"have":[49],"been":[50],"widely":[51],"used":[52],"various":[54],"tasks":[55],"speech,":[60],"such":[61],"as":[62],"automatic":[63],"speech":[64],"recognition,":[65],"audio":[66],"tagging,":[67],"etc.":[68],"If":[69],"training":[71],"dataset":[72,164],"large":[74],"general":[76],"enough,":[77],"embedding":[79],"features":[80,113,152],"extracted":[81],"by":[82,156],"will":[86],"cover":[87],"potential":[89],"information":[90],"original":[93,117],"task.":[94],"We":[95],"use":[96],"PANNs":[99,115],"which":[100],"suitable":[102],"for":[103],"proposed":[107],"two":[108],"methods":[109],"fuse":[111],"model,":[118],"respectively.":[119],"addition,":[121],"also":[123],"propose":[124],"a":[125],"weight":[126],"raised":[127],"temporal":[128],"contrastive":[129],"loss":[130],"improve":[132],"model\u2019s":[134],"switching":[135],"speed":[136],"at":[137],"boundaries":[139],"smoothness":[142],"within":[143],"events.":[144],"Experimental":[145],"results":[146],"show":[147],"that":[148],"using":[149],"outperforms":[153],"baseline":[155],"8.5%":[157],"9.1%":[159],"DESED":[161],"public":[162],"evaluation":[163],"terms":[166],"polyphonic":[168],"score":[171],"(PSDS).":[172]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}