{"id":"https://openalex.org/W4402569726","doi":"https://doi.org/10.1109/taslp.2024.3446232","title":"AudioNet: Supervised Deep Hashing for Retrieval of Similar Audio Events","display_name":"AudioNet: Supervised Deep Hashing for Retrieval of Similar Audio Events","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402569726","doi":"https://doi.org/10.1109/taslp.2024.3446232"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3446232","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3446232","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.01372","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052969947","display_name":"Sagar Dutta","orcid":"https://orcid.org/0000-0002-8371-744X"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Sagar Dutta","raw_affiliation_strings":["RITMO Centre for Interdisciplinary Studies in Rhythm, Time and Motion, Department of Musicology, University of Oslo, Oslo, Norway"],"affiliations":[{"raw_affiliation_string":"RITMO Centre for Interdisciplinary Studies in Rhythm, Time and Motion, Department of Musicology, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011121139","display_name":"Vipul Arora","orcid":"https://orcid.org/0000-0002-1207-1258"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vipul Arora","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology Kanpur, Kanpur, Uttar Pradesh, India"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology Kanpur, Kanpur, Uttar Pradesh, India","institution_ids":["https://openalex.org/I94234084"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5052969947"],"corresponding_institution_ids":["https://openalex.org/I184942183"],"apc_list":null,"apc_paid":null,"fwci":0.3504,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55196562,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"32","issue":null,"first_page":"4526","last_page":"4536"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9921000003814697,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9822999835014343,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6974801421165466},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6196099519729614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41043317317962646},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.368672251701355},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3294464945793152},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.06340807676315308}],"concepts":[{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6974801421165466},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6196099519729614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41043317317962646},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.368672251701355},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3294464945793152},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.06340807676315308}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2024.3446232","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3446232","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2511.01372","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.01372","pdf_url":"https://arxiv.org/pdf/2511.01372","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:www.duo.uio.no:10852/114458","is_oa":true,"landing_page_url":"http://hdl.handle.net/10852/114458","pdf_url":null,"source":{"id":"https://openalex.org/S4306401717","display_name":"Duo Research Archive (University of Oslo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184942183","host_organization_name":"University of Oslo","host_organization_lineage":["https://openalex.org/I184942183"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2329-9290","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2511.01372","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.01372","pdf_url":"https://arxiv.org/pdf/2511.01372","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4402569726.pdf"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1910300841","https://openalex.org/W1974647172","https://openalex.org/W1992371516","https://openalex.org/W2044195942","https://openalex.org/W2052666245","https://openalex.org/W2124509324","https://openalex.org/W2138621090","https://openalex.org/W2162499636","https://openalex.org/W2194775991","https://openalex.org/W2282691309","https://openalex.org/W2508837377","https://openalex.org/W2520774990","https://openalex.org/W2566935005","https://openalex.org/W2586937979","https://openalex.org/W2593116425","https://openalex.org/W2594783837","https://openalex.org/W2618530766","https://openalex.org/W2890913619","https://openalex.org/W2914327968","https://openalex.org/W2940994217","https://openalex.org/W2969985801","https://openalex.org/W2979656080","https://openalex.org/W2982662945","https://openalex.org/W3009806461","https://openalex.org/W3015505732","https://openalex.org/W3087290310","https://openalex.org/W3094550259","https://openalex.org/W3173956867","https://openalex.org/W3197988356","https://openalex.org/W3198351537","https://openalex.org/W3203004311","https://openalex.org/W4210913346","https://openalex.org/W4293075380","https://openalex.org/W4312095884","https://openalex.org/W4372347661","https://openalex.org/W4391545855","https://openalex.org/W6604987197","https://openalex.org/W6637373629","https://openalex.org/W6688152296","https://openalex.org/W6688844344","https://openalex.org/W6691474080","https://openalex.org/W6697214482","https://openalex.org/W6737664043","https://openalex.org/W6738979955","https://openalex.org/W6753583920","https://openalex.org/W6754813029","https://openalex.org/W6790759947","https://openalex.org/W6801929243"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"This":[0,137],"work":[1,205],"presents":[2],"a":[3,19,36,82,207],"supervised":[4],"deep":[5,221],"hashing":[6,24,71],"method":[7,121,161,193],"for":[8,22,52,156,209],"retrieving":[9],"similar":[10,28,53,91,217],"audio":[11,29,33,54,92,117,218,222],"events.":[12,93],"The":[13,120,159,178,200],"proposed":[14,99,160,192],"method,":[15],"named":[16],"AudioNet,":[17],"is":[18,98],"deep-learning-based":[20],"system":[21],"efficient":[23,214],"and":[25,62,66,104],"retrieval":[26,41,88,164,195,215],"of":[27,90,116,190,216],"events":[30,219],"using":[31,147,220],"an":[32],"example":[34],"as":[35,166],"query.":[37],"AudioNet":[38],"achieves":[39],"high":[40],"performance":[42,89,196],"on":[43,76,212],"multiple":[44,198],"standard":[45,77,148],"datasets":[46],"by":[47,168],"generating":[48],"binary":[49],"hash":[50,145],"codes":[51,146],"events,":[55],"setting":[56],"new":[57],"benchmarks":[58],"in":[59,85,182,194,203],"the":[60,87,114,139,143,169,187,191,213],"field,":[61],"highlighting":[63],"its":[64],"efficacy":[65],"effectiveness":[67],"compare":[68],"to":[69,112,129,141],"other":[70],"methods.":[72],"Through":[73],"comprehensive":[74],"experiments":[75],"datasets,":[78],"our":[79],"research":[80],"represents":[81],"pioneering":[83],"effort":[84],"evaluating":[86],"A":[94],"novel":[95],"loss":[96,107],"function":[97],"which":[100,126,152],"incorporates":[101],"weighted":[102,105],"contrastive":[103],"pairwise":[106],"along":[108],"with":[109,175],"hashcode":[110],"balancing":[111],"improve":[113],"efficiency":[115],"event":[118],"retrieval.":[119],"adopts":[122],"discrete":[123,133,144],"gradient":[124],"propagation,":[125],"allows":[127],"gradients":[128],"be":[130],"propagated":[131],"through":[132],"variables":[134],"during":[135],"backpropagation.":[136],"enables":[138],"network":[140],"optimize":[142],"gradient-based":[149],"optimization":[150],"algorithms,":[151],"are":[153],"typically":[154],"used":[155],"continuous":[157],"variables.":[158],"showcases":[162],"promising":[163],"performance,":[165],"evidenced":[167],"experimental":[170],"results,":[171],"even":[172],"when":[173],"dealing":[174],"imbalanced":[176],"datasets.":[177,199],"systematic":[179],"analysis":[180],"conducted":[181],"this":[183,204],"study":[184],"further":[185],"supports":[186],"significant":[188],"benefits":[189],"across":[197],"findings":[201],"presented":[202],"establish":[206],"baseline":[208],"future":[210],"studies":[211],"embeddings.":[223]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}