{"id":"https://openalex.org/W2809183397","doi":"https://doi.org/10.1145/3214366","title":"A Human-in-the-Loop System for Sound Event Detection and Annotation","display_name":"A Human-in-the-Loop System for Sound Event Detection and Annotation","publication_year":2018,"publication_date":"2018-06-21","ids":{"openalex":"https://openalex.org/W2809183397","doi":"https://doi.org/10.1145/3214366","mag":"2809183397"},"language":"en","primary_location":{"id":"doi:10.1145/3214366","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3214366","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3214366","source":{"id":"https://openalex.org/S4210173818","display_name":"ACM Transactions on Interactive Intelligent Systems","issn_l":"2160-6455","issn":["2160-6455","2160-6463"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Interactive Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3214366","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103276814","display_name":"Bongjun Kim","orcid":"https://orcid.org/0000-0002-5142-0262"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bongjun Kim","raw_affiliation_strings":["Northwestern University, USA"],"affiliations":[{"raw_affiliation_string":"Northwestern University, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102878078","display_name":"Bryan Pardo","orcid":"https://orcid.org/0000-0002-1427-6492"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bryan Pardo","raw_affiliation_strings":["Northwestern University, USA"],"affiliations":[{"raw_affiliation_string":"Northwestern University, USA","institution_ids":["https://openalex.org/I111979921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103276814"],"corresponding_institution_ids":["https://openalex.org/I111979921"],"apc_list":null,"apc_paid":null,"fwci":3.4832,"has_fulltext":true,"cited_by_count":45,"citation_normalized_percentile":{"value":0.93679399,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"8","issue":"2","first_page":"1","last_page":"23"},"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":0.9997000098228455,"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":0.9987000226974487,"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":0.8290367126464844},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6361039280891418},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5059136748313904},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5030915141105652},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49257785081863403},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.45412153005599976},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.45242416858673096},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.41518133878707886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4061625301837921},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32722896337509155},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.10632213950157166},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08824563026428223}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8290367126464844},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6361039280891418},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5059136748313904},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5030915141105652},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49257785081863403},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.45412153005599976},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.45242416858673096},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.41518133878707886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4061625301837921},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32722896337509155},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.10632213950157166},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08824563026428223},{"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/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"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:10.1145/3214366","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3214366","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3214366","source":{"id":"https://openalex.org/S4210173818","display_name":"ACM Transactions on Interactive Intelligent Systems","issn_l":"2160-6455","issn":["2160-6455","2160-6463"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Interactive Intelligent Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3214366","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3214366","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3214366","source":{"id":"https://openalex.org/S4210173818","display_name":"ACM Transactions on Interactive Intelligent Systems","issn_l":"2160-6455","issn":["2160-6455","2160-6463"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Interactive Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G2278759209","display_name":null,"funder_award_id":"1617497","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2809183397.pdf","grobid_xml":"https://content.openalex.org/works/W2809183397.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W68855703","https://openalex.org/W131100585","https://openalex.org/W161531308","https://openalex.org/W395933519","https://openalex.org/W1255693054","https://openalex.org/W1520047127","https://openalex.org/W1569206690","https://openalex.org/W1908985308","https://openalex.org/W1987426045","https://openalex.org/W2004959592","https://openalex.org/W2024341900","https://openalex.org/W2024550919","https://openalex.org/W2026259539","https://openalex.org/W2026566343","https://openalex.org/W2041617562","https://openalex.org/W2041823554","https://openalex.org/W2057843461","https://openalex.org/W2059841424","https://openalex.org/W2062529116","https://openalex.org/W2086384421","https://openalex.org/W2109378394","https://openalex.org/W2109832419","https://openalex.org/W2116206474","https://openalex.org/W2124332348","https://openalex.org/W2124351162","https://openalex.org/W2127058057","https://openalex.org/W2127135195","https://openalex.org/W2127779812","https://openalex.org/W2135131618","https://openalex.org/W2141061845","https://openalex.org/W2141282920","https://openalex.org/W2143562257","https://openalex.org/W2157018954","https://openalex.org/W2158648028","https://openalex.org/W2239493168","https://openalex.org/W2341412280","https://openalex.org/W2397131144","https://openalex.org/W2403761853","https://openalex.org/W2526050071","https://openalex.org/W2594302303","https://openalex.org/W4237305599","https://openalex.org/W4248635988"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2625833328","https://openalex.org/W4405124681","https://openalex.org/W1533177136","https://openalex.org/W4380994516"],"abstract_inverted_index":{"Labeling":[0],"of":[1,59,132,159,192,238],"audio":[2,19,114,134,152],"events":[3,12,97,177],"is":[4,21,29,40],"essential":[5],"for":[6,75],"many":[7,50,76],"tasks.":[8],"However,":[9],"finding":[10],"sound":[11,86,96,176],"and":[13,23,201],"labeling":[14,66,74,87,153,182,231],"them":[15,183],"within":[16],"a":[17,35,56,84,91,99,104,112,149,164,236],"long":[18,100,113],"file":[20,115],"tedious":[22],"time-consuming.":[24],"In":[25,185],"cases":[26],"where":[27],"there":[28,139],"very":[30],"little":[31],"labeled":[32,37,143],"data":[33],"(e.g.,":[34,52,116,145],"single":[36],"example),":[38],"it":[39,171],"often":[41],"not":[42,68,223],"feasible":[43],"to":[44,110,147,187],"train":[45,148],"an":[46,218],"automatic":[47],"labeler":[48],"because":[49],"techniques":[51],"deep":[53],"learning)":[54],"require":[55],"large":[57],"number":[58],"human-labeled":[60],"training":[61],"examples.":[62],"Also,":[63],"fully":[64],"automated":[65],"may":[67],"show":[69,169],"sufficient":[70],"agreement":[71],"with":[72],"human":[73],"uses.":[77],"To":[78,155],"solve":[79],"this":[80],"issue,":[81],"we":[82,162,196],"present":[83],"human-in-the-loop":[85],"system":[88],"that":[89,122,170,209,217,221],"helps":[90],"user":[92,105],"quickly":[93],"label":[94,111,174],"target":[95,120,175],"in":[98],"audio.":[101],"It":[102],"lets":[103],"reduce":[106],"the":[107,127,133,136,157,189,193,211],"time":[108],"required":[109],"20":[117],"hours)":[118],"containing":[119],"sounds":[121],"are":[123,140,205],"sparsely":[124],"distributed":[125],"throughout":[126],"recording":[128],"(10%":[129],"or":[130],"less":[131],"contains":[135],"target)":[137],"when":[138],"too":[141],"few":[142],"examples":[144],"one)":[146],"state-of-the-art":[150],"machine":[151,202],"system.":[154],"evaluate":[156],"effectiveness":[158],"our":[160],"tool,":[161],"performed":[163],"human-subject":[165],"study.":[166],"The":[167,214],"results":[168],"helped":[172],"participants":[173],"twice":[178],"as":[179,181,233,235],"fast":[180],"manually.":[184],"addition":[186],"measuring":[188],"overall":[190,212],"performance":[191],"proposed":[194],"system,":[195],"also":[197],"measure":[198],"interaction":[199,225],"overhead":[200,226],"accuracy,":[203],"which":[204],"two":[206],"key":[207],"factors":[208],"determine":[210],"performance.":[213],"analysis":[215],"shows":[216],"ideal":[219],"interface":[220],"does":[222],"have":[224],"at":[227],"all":[228],"could":[229],"speed":[230],"by":[232],"much":[234],"factor":[237],"four.":[239]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":5}],"updated_date":"2026-03-15T09:29:46.208133","created_date":"2025-10-10T00:00:00"}