{"id":"https://openalex.org/W4416251790","doi":"https://doi.org/10.1109/waspaa66052.2025.11230980","title":"SynSonic: Augmenting Sound Event Detection through Text-to-Audio Diffusion ControlNet and Effective Sample Filtering","display_name":"SynSonic: Augmenting Sound Event Detection through Text-to-Audio Diffusion ControlNet and Effective Sample Filtering","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416251790","doi":"https://doi.org/10.1109/waspaa66052.2025.11230980"},"language":null,"primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230980","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230980","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5048171604","display_name":"Jiarui Hai","orcid":"https://orcid.org/0000-0001-9968-7372"},"institutions":[{"id":"https://openalex.org/I2802946424","display_name":"Johns Hopkins University Applied Physics Laboratory","ror":"https://ror.org/029pp9z10","country_code":"US","type":"facility","lineage":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]},{"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":true,"raw_author_name":"Jiarui Hai","raw_affiliation_strings":["Johns Hopkins University,Department of Electrical and Computer Engineering,Maryland,USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Department of Electrical and Computer Engineering,Maryland,USA","institution_ids":["https://openalex.org/I2802946424","https://openalex.org/I145311948","https://openalex.org/I2799853436"]}]},{"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/I2802946424","display_name":"Johns Hopkins University Applied Physics Laboratory","ror":"https://ror.org/029pp9z10","country_code":"US","type":"facility","lineage":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]},{"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,Maryland,USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Department of Electrical and Computer Engineering,Maryland,USA","institution_ids":["https://openalex.org/I2802946424","https://openalex.org/I145311948","https://openalex.org/I2799853436"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5048171604"],"corresponding_institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2799853436","https://openalex.org/I2802946424"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45541385,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.9492999911308289,"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":0.9492999911308289,"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":0.01810000091791153,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.007699999958276749,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/event","display_name":"Event (particle physics)","score":0.5820000171661377},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5149000287055969},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4797999858856201},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4674000144004822},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4049000144004822},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.39309999346733093},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3797000050544739},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.376800000667572}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7062000036239624},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5820000171661377},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5149000287055969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4860999882221222},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4797999858856201},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4674000144004822},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4049000144004822},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.39309999346733093},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3797000050544739},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.376800000667572},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.37139999866485596},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3580999970436096},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3483999967575073},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3456000089645386},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2827000021934509},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.26010000705718994}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230980","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230980","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2408239454","https://openalex.org/W2593116425","https://openalex.org/W2771361008","https://openalex.org/W2936774411","https://openalex.org/W2945761034","https://openalex.org/W2959539607","https://openalex.org/W3006275583","https://openalex.org/W3015190346","https://openalex.org/W3162999565","https://openalex.org/W3178592608","https://openalex.org/W4221149441","https://openalex.org/W4307823382","https://openalex.org/W4372260310","https://openalex.org/W4385823166","https://openalex.org/W4390873054","https://openalex.org/W4392903172","https://openalex.org/W4393154248","https://openalex.org/W4398226295","https://openalex.org/W4402112407","https://openalex.org/W4403653559","https://openalex.org/W4408351785","https://openalex.org/W4408352247","https://openalex.org/W4415433415"],"related_works":[],"abstract_inverted_index":{"Data":[0],"synthesis":[1],"and":[2,24,61,74,118,138,144],"augmentation":[3,20,77,85],"are":[4],"essential":[5],"for":[6,78,88],"Sound":[7,134],"Event":[8],"Detection":[9,135],"(SED)":[10],"due":[11,53],"to":[12,49,54,101],"the":[13,34,55,62],"scarcity":[14],"of":[15,36,57,64],"temporally":[16,103],"labeled":[17],"data.":[18],"While":[19],"methods":[21],"like":[22],"SpecAugment":[23],"Mix-up":[25],"can":[26],"enhance":[27],"model":[28],"performance,":[29],"they":[30],"remain":[31],"constrained":[32],"by":[33,97],"diversity":[35],"existing":[37],"samples.":[38],"Recent":[39],"generative":[40],"models":[41,95],"offer":[42],"new":[43],"opportunities,":[44],"yet":[45],"their":[46],"direct":[47],"application":[48],"SED":[50],"is":[51],"challenging":[52],"lack":[56],"precise":[58],"temporal":[59,142],"annotations":[60],"risk":[63],"introducing":[65],"noise":[66],"through":[67],"unreliable":[68],"filtering.":[69],"To":[70],"address":[71],"these":[72],"challenges":[73],"enable":[75],"generative-based":[76],"SED,":[79],"we":[80,119],"propose":[81],"SynSonic,":[82],"a":[83],"data":[84],"method":[86],"tailored":[87],"this":[89],"task.":[90],"SynSonic":[91,131],"leverages":[92],"text-to-audio":[93],"diffusion":[94],"guided":[96],"an":[98],"energy-envelope":[99],"ControlNet":[100],"generate":[102],"coherent":[104],"sound":[105,145],"events.":[106],"A":[107],"joint":[108],"score":[109],"filtering":[110],"strategy":[111],"with":[112],"dual":[113],"classifiers":[114],"ensures":[115],"sample":[116],"quality,":[117],"explore":[120],"its":[121],"practical":[122],"integration":[123],"into":[124],"training":[125],"pipelines.":[126],"Experimental":[127],"results":[128],"show":[129],"that":[130],"improves":[132],"Polyphonic":[133],"Scores":[136],"(PSDS1":[137],"PSDS2),":[139],"enhancing":[140],"both":[141],"localization":[143],"class":[146],"discrimination.":[147]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}