{"id":"https://openalex.org/W3015505732","doi":"https://doi.org/10.1109/icassp40776.2020.9053766","title":"Supervised Deep Hashing for Efficient Audio Event Retrieval","display_name":"Supervised Deep Hashing for Efficient Audio Event Retrieval","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015505732","doi":"https://doi.org/10.1109/icassp40776.2020.9053766","mag":"3015505732"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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":true,"raw_author_name":"Arindam Jati","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034420214","display_name":"Dimitra Emmanouilidou","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dimitra Emmanouilidou","raw_affiliation_strings":["Audio and Acoustics Research Group, Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Audio and Acoustics Research Group, Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5067289130"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.7577,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.69644503,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4497","last_page":"4501"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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/T10860","display_name":"Speech and Audio Processing","score":0.996999979019165,"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/computer-science","display_name":"Computer science","score":0.8144242763519287},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6818448901176453},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6059294939041138},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4028885066509247},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.17326033115386963}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8144242763519287},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6818448901176453},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6059294939041138},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4028885066509247},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.17326033115386963},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1939575207","https://openalex.org/W1974647172","https://openalex.org/W1993625798","https://openalex.org/W2005666490","https://openalex.org/W2012833704","https://openalex.org/W2052666245","https://openalex.org/W2086384421","https://openalex.org/W2096665203","https://openalex.org/W2103279261","https://openalex.org/W2110458017","https://openalex.org/W2124509324","https://openalex.org/W2130660124","https://openalex.org/W2135131618","https://openalex.org/W2171572695","https://openalex.org/W2251864938","https://openalex.org/W2293597654","https://openalex.org/W2293824885","https://openalex.org/W2411707397","https://openalex.org/W2526050071","https://openalex.org/W2562322388","https://openalex.org/W2562786159","https://openalex.org/W2593116425","https://openalex.org/W2884535146","https://openalex.org/W2897656415","https://openalex.org/W2936044260","https://openalex.org/W2962910554","https://openalex.org/W2963906190","https://openalex.org/W4230940751","https://openalex.org/W4254197176","https://openalex.org/W6691474080","https://openalex.org/W6697060382","https://openalex.org/W6697214482","https://openalex.org/W6730778485","https://openalex.org/W6730864085","https://openalex.org/W6753583920","https://openalex.org/W6755679164"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"Efficient":[0],"retrieval":[1,96,136],"of":[2,9,20,41,51,84,123],"audio":[3,26,32,102,124,134],"events":[4],"can":[5],"facilitate":[6],"real-time":[7],"implementation":[8],"numerous":[10],"query":[11],"and":[12,88,108,112,138],"search-based":[13],"systems.":[14],"This":[15,126],"work":[16,127],"investigates":[17],"the":[18,65,85,95,121],"potency":[19],"different":[21],"hashing":[22,45,61,114],"techniques":[23],"for":[24,36,74,143],"efficient":[25,75,133],"event":[27,103,135],"retrieval.":[28],"Multiple":[29],"state-of-the-art":[30],"weak":[31,66],"embeddings":[33,67],"are":[34],"employed":[35,101],"this":[37],"purpose.":[38],"The":[39,78,105],"performance":[40],"four":[42],"classical":[43],"unsupervised":[44,113],"algorithms":[46],"is":[47,89],"explored":[48],"as":[49],"part":[50],"off-the-shelf":[52],"analysis.":[53],"Then,":[54],"we":[55],"propose":[56],"a":[57,69,82,129],"partially":[58],"supervised":[59,111],"deep":[60],"framework":[62],"that":[63],"transforms":[64],"into":[68],"low-dimensional":[70],"space":[71],"while":[72],"optimizing":[73],"hash":[76],"codes.":[77],"model":[79],"uses":[80],"only":[81],"fraction":[83],"available":[86],"labels":[87],"shown":[90],"here":[91],"to":[92,140],"significantly":[93],"improve":[94],"accuracy":[97],"on":[98,120],"two":[99],"widely":[100],"datasets.":[104],"extensive":[106],"analysis":[107],"comparison":[109],"between":[110],"methods":[115],"presented":[116],"here,":[117],"give":[118],"insights":[119],"quantizability":[122],"embeddings.":[125],"provides":[128],"first":[130],"look":[131],"in":[132],"systems":[137],"hopes":[139],"set":[141],"baselines":[142],"future":[144],"research.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}
