{"id":"https://openalex.org/W2793928107","doi":"https://doi.org/10.1145/3172944.3173149","title":"Leveraging User Input and Feedback for Interactive Sound Event Detection and Annotation","display_name":"Leveraging User Input and Feedback for Interactive Sound Event Detection and Annotation","publication_year":2018,"publication_date":"2018-03-05","ids":{"openalex":"https://openalex.org/W2793928107","doi":"https://doi.org/10.1145/3172944.3173149","mag":"2793928107"},"language":"en","primary_location":{"id":"doi:10.1145/3172944.3173149","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3172944.3173149","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"23rd International Conference on Intelligent User Interfaces","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/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, Evanston, IL, USA"],"affiliations":[{"raw_affiliation_string":"Northwestern University, Evanston, IL, USA","institution_ids":["https://openalex.org/I111979921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5103276814"],"corresponding_institution_ids":["https://openalex.org/I111979921"],"apc_list":null,"apc_paid":null,"fwci":0.4954,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.61605781,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"671","last_page":"672"},"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":0.9980000257492065,"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":0.9945999979972839,"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":0.8714604377746582},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.668840765953064},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5337140560150146},{"id":"https://openalex.org/keywords/audio-feedback","display_name":"Audio feedback","score":0.5307925343513489},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5172843933105469},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4607904851436615},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.41798868775367737},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4069347083568573},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40558624267578125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37659379839897156},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3491115868091583}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8714604377746582},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.668840765953064},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5337140560150146},{"id":"https://openalex.org/C38956757","wikidata":"https://www.wikidata.org/wiki/Q716215","display_name":"Audio feedback","level":2,"score":0.5307925343513489},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5172843933105469},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4607904851436615},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.41798868775367737},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4069347083568573},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40558624267578125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37659379839897156},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3491115868091583},{"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},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3172944.3173149","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3172944.3173149","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"23rd International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"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"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2109378394","https://openalex.org/W2119770538","https://openalex.org/W2341412280","https://openalex.org/W2403761853","https://openalex.org/W2594302303"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2361861616"],"abstract_inverted_index":{"Tagging":[0],"of":[1,45,80,83,92,114,124],"environment":[2],"audio":[3,20,122],"events":[4,13],"is":[5,22,35,51],"essential":[6],"in":[7,130],"many":[8],"areas.":[9],"However,":[10],"finding":[11],"sound":[12,61,88],"and":[14,24,49,104,127],"labeling":[15],"them":[16],"within":[17],"a":[18,42,141],"long":[19],"file":[21],"tedious":[23],"time-consuming.":[25],"Building":[26],"an":[27],"automatic":[28],"recognition":[29],"system":[30],"using":[31],"modern":[32],"machine":[33,70],"learning":[34],"often":[36],"not":[37,52,136],"feasible":[38],"because":[39],"it":[40,50],"requires":[41],"large":[43],"number":[44],"human-labeled":[46],"training":[47,138],"examples":[48,139],"reliable":[53],"enough":[54,137],"for":[55,140],"all":[56],"uses.":[57],"I":[58,96,107],"propose":[59],"interactive":[60,87],"event":[62],"detection":[63],"to":[64,85],"solve":[65],"the":[66,78,86,131],"issue":[67],"by":[68],"combining":[69],"search":[71],"with":[72],"human":[73],"tagging,":[74],"specifically":[75],"focusing":[76],"on":[77],"effectiveness":[79],"various":[81],"types":[82,91],"user-inputs":[84],"searching.":[89],"The":[90],"user":[93,116],"inputs":[94,117],"that":[95,109],"will":[97],"explore":[98],"include":[99],"binary":[100],"relevance":[101],"feedback,":[102],"segmentation,":[103],"vocal":[105],"imitation.":[106],"expect":[108],"leveraging":[110],"one":[111],"or":[112],"combination":[113],"these":[115],"would":[118],"help":[119],"users":[120],"find":[121],"contents":[123],"interest":[125],"quickly":[126],"accurately,":[128],"even":[129],"situation":[132],"where":[133],"there":[134],"are":[135],"typical":[142],"automated":[143],"system.":[144]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
