{"id":"https://openalex.org/W4416250455","doi":"https://doi.org/10.1109/waspaa66052.2025.11230981","title":"Sound event detection with audio-text models and heterogeneous temporal annotations","display_name":"Sound event detection with audio-text models and heterogeneous temporal annotations","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416250455","doi":"https://doi.org/10.1109/waspaa66052.2025.11230981"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230981","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230981","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/A5030053674","display_name":"Manu Harju","orcid":null},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Manu Harju","raw_affiliation_strings":["Tampere University,Signal Processing Research Centre,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University,Signal Processing Research Centre,Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079981416","display_name":"Annamaria Mesaros","orcid":"https://orcid.org/0000-0002-6640-9752"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Annamaria Mesaros","raw_affiliation_strings":["Tampere University,Signal Processing Research Centre,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University,Signal Processing Research Centre,Finland","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.064,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82296772,"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":"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":0.9785000085830688,"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":0.9785000085830688,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.005499999970197678,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.004900000058114529,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.7508999705314636},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7301999926567078},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5180000066757202},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4212000072002411},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.41339999437332153},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4050999879837036},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.3817000091075897},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.367000013589859},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.36059999465942383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7973999977111816},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.7508999705314636},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7301999926567078},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5389000177383423},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5180000066757202},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47850000858306885},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42149999737739563},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4212000072002411},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41339999437332153},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4050999879837036},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3817000091075897},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.367000013589859},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C77265313","wikidata":"https://www.wikidata.org/wiki/Q879844","display_name":"Rest (music)","level":2,"score":0.34540000557899475},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.30250000953674316},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2768999934196472},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C2780646970","wikidata":"https://www.wikidata.org/wiki/Q6980787","display_name":"Natural sounds","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.26899999380111694},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C2987896495","wikidata":"https://www.wikidata.org/wiki/Q5416716","display_name":"Event data","level":3,"score":0.2603999972343445},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2524000108242035},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230981","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230981","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"},{"id":"pmh:oai:trepo.tuni.fi:10024/233644","is_oa":false,"landing_page_url":"https://trepo.tuni.fi/handle/10024/233644","pdf_url":null,"source":{"id":"https://openalex.org/S7407055260","display_name":"Trepo - Institutional Repository of Tampere University","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2408239454","https://openalex.org/W2593116425","https://openalex.org/W2936774411","https://openalex.org/W2959539607","https://openalex.org/W2962784628","https://openalex.org/W3015190346","https://openalex.org/W3162999565","https://openalex.org/W3178592608","https://openalex.org/W3201143670","https://openalex.org/W3204267711","https://openalex.org/W4372260310","https://openalex.org/W4372260340","https://openalex.org/W4385245566","https://openalex.org/W4385822843","https://openalex.org/W4400033239","https://openalex.org/W4404609021","https://openalex.org/W4405934446","https://openalex.org/W4408353237","https://openalex.org/W4408353596","https://openalex.org/W4408354908","https://openalex.org/W4411688496"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,17,102],"generating":[3],"synthetic":[4,97],"captions":[5,47,98],"based":[6],"on":[7],"audio":[8,24],"and":[9,57,83,137],"related":[10],"metadata":[11],"allow":[12],"using":[13,61],"the":[14,52,59,77,84,100,107,124,145],"information":[15,50],"contained":[16],"natural":[18],"language":[19],"as":[20,48],"input":[21],"for":[22,55,112],"other":[23],"tasks.":[25],"In":[26,67],"this":[27],"paper,":[28],"we":[29,69],"propose":[30],"a":[31,36,71,117],"novel":[32],"method":[33],"to":[34,51,106,130,140],"guide":[35],"sound":[37,113],"event":[38,114],"detection":[39],"system":[40],"with":[41,134],"free-form":[42],"text.":[43],"We":[44],"use":[45],"machine-generated":[46],"complementary":[49],"strong":[53,81,135],"labels":[54],"training,":[56],"evaluate":[58],"systems":[60],"different":[62],"types":[63],"of":[64,76,86,119,144],"textual":[65],"inputs.":[66],"addition,":[68],"study":[70],"scenario":[72],"where":[73],"only":[74,88,149],"part":[75],"training":[78,146],"data":[79,147],"has":[80,89,148],"labels,":[82,136],"rest":[85],"it":[87],"temporally":[90],"weak":[91,150],"labels.":[92,151],"Our":[93],"findings":[94],"show":[95],"that":[96],"improve":[99],"performance":[101],"both":[103],"cases":[104],"compared":[105],"CRNN":[108],"architecture":[109],"typically":[110],"used":[111],"detection.":[115],"On":[116],"dataset":[118],"50":[120],"highly":[121],"unbalanced":[122],"classes,":[123],"PSDS-1":[125],"score":[126],"increases":[127],"from":[128,138],"0.223":[129],"0.277":[131],"when":[132,142],"trained":[133],"0.166":[139],"0.218":[141],"half":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-14T00:00:00"}