{"id":"https://openalex.org/W2936044260","doi":"https://doi.org/10.1109/icassp.2019.8682341","title":"Hierarchy-aware Loss Function on a Tree Structured Label Space for Audio Event Detection","display_name":"Hierarchy-aware Loss Function on a Tree Structured Label Space for Audio Event Detection","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2936044260","doi":"https://doi.org/10.1109/icassp.2019.8682341","mag":"2936044260"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682341","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5067289130","display_name":"Arindam Jati","orcid":"https://orcid.org/0000-0002-9498-8536"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arindam Jati","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076053477","display_name":"Naveen Kumar","orcid":"https://orcid.org/0000-0003-3401-6927"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naveen Kumar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081135618","display_name":"Ruxin Chen","orcid":"https://orcid.org/0009-0000-0624-4127"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruxin Chen","raw_affiliation_strings":["SONY Interactive Entertainment LLC, San Mateo, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SONY Interactive Entertainment LLC, San Mateo, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021678540","display_name":"Panayiotis Georgiou","orcid":"https://orcid.org/0000-0002-0790-7161"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Panayiotis Georgiou","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0584,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.92470378,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6","last_page":"10"},"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":0.998199999332428,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9772999882698059,"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":0.7784504890441895},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.6412850618362427},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5525866150856018},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5476162433624268},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5466629862785339},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5262141227722168},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.48916390538215637},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45083677768707275},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.44747161865234375},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.44295981526374817},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4260070025920868},{"id":"https://openalex.org/keywords/multi-label-classification","display_name":"Multi-label classification","score":0.4119395315647125},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4109850525856018},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40327560901641846},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3436993956565857},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.28538501262664795},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10081341862678528}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7784504890441895},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.6412850618362427},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5525866150856018},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5476162433624268},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5466629862785339},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5262141227722168},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.48916390538215637},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45083677768707275},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.44747161865234375},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.44295981526374817},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4260070025920868},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.4119395315647125},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4109850525856018},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40327560901641846},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3436993956565857},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28538501262664795},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10081341862678528},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682341","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1501987291","https://openalex.org/W1566352582","https://openalex.org/W1993625798","https://openalex.org/W2005666490","https://openalex.org/W2038484192","https://openalex.org/W2048174296","https://openalex.org/W2086384421","https://openalex.org/W2096733369","https://openalex.org/W2101234009","https://openalex.org/W2103279261","https://openalex.org/W2115447976","https://openalex.org/W2130640900","https://openalex.org/W2135131618","https://openalex.org/W2139855016","https://openalex.org/W2157364932","https://openalex.org/W2163922914","https://openalex.org/W2165698076","https://openalex.org/W2194775991","https://openalex.org/W2325939864","https://openalex.org/W2398456099","https://openalex.org/W2517626051","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2624871570","https://openalex.org/W2963543871","https://openalex.org/W2963723765","https://openalex.org/W2964189431","https://openalex.org/W2964345931","https://openalex.org/W3099206234","https://openalex.org/W3173562241","https://openalex.org/W4235169531","https://openalex.org/W6633898140","https://openalex.org/W6675354045","https://openalex.org/W6700903540","https://openalex.org/W6712469065","https://openalex.org/W6726421819","https://openalex.org/W6739365718","https://openalex.org/W6797055875"],"related_works":["https://openalex.org/W2365264209","https://openalex.org/W2509431957","https://openalex.org/W2026999166","https://openalex.org/W1599954583","https://openalex.org/W4211007821","https://openalex.org/W2802395037","https://openalex.org/W4389565704","https://openalex.org/W4386076580","https://openalex.org/W3095707208","https://openalex.org/W2994927414"],"abstract_inverted_index":{"The":[0,26,104,124,143],"paper":[1],"introduces":[2],"a":[3,8,20,74,85,93,109],"hierarchy-aware":[4,63,121],"loss":[5,64,68,76,119,122],"function":[6],"in":[7,40,61,108,156],"Deep":[9],"Neural":[10],"Network":[11],"for":[12,100,174],"an":[13,169],"audio":[14,33,49,152],"event":[15,34],"detection":[16,35],"task":[17],"that":[18,59],"has":[19],"bi-level":[21,101],"tree":[22,55],"structured":[23],"label":[24,42,54,102],"space.":[25],"goal":[27],"is":[28,82,89,92,106,127,146,163,172],"not":[29],"only":[30],"to":[31,46,57,129,149,165],"improve":[32],"performance":[36],"at":[37,137],"all":[38],"levels":[39,139],"the":[41,53,62,131,141,161],"hierarchy,":[43],"but":[44],"also":[45,147],"produce":[47],"better":[48,151],"embeddings.":[50],"We":[51],"exploit":[52],"structure":[56],"preserve":[58],"information":[60],"function.":[65,123],"Two":[66],"different":[67],"functions":[69],"are":[70],"separately":[71],"employed.":[72],"First,":[73],"triplet":[75,98],"with":[77],"probabilistic":[78],"multi-level":[79],"batch":[80],"mining":[81],"introduced.":[83],"Second,":[84],"quadruplet":[86],"learning":[87,99,111],"method":[88,126],"applied,":[90],"which":[91],"special":[94],"case":[95],"of":[96,140],"generalized":[97],"taxonomy.":[103],"training":[105],"performed":[107],"multi-task":[110,144],"framework":[112],"by":[113],"jointly":[114],"optimizing":[115],"cross":[116,133],"entropy":[117,134],"based":[118,135],"and":[120],"proposed":[125],"found":[128],"outperform":[130],"baseline":[132],"models":[136],"both":[138],"hierarchy.":[142],"model":[145,162],"able":[148],"learn":[150],"representations":[153],"as":[154],"observed":[155],"our":[157],"clustering":[158],"experiments.":[159],"Moreover,":[160],"shown":[164],"transfer":[166],"well":[167],"when":[168],"out-of-domain":[170],"dataset":[171],"used":[173],"evaluation.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}