{"id":"https://openalex.org/W4403792443","doi":"https://doi.org/10.1145/3664647.3681647","title":"AMG-Embedding: A Self-Supervised Embedding Approach for Audio Identification","display_name":"AMG-Embedding: A Self-Supervised Embedding Approach for Audio Identification","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792443","doi":"https://doi.org/10.1145/3664647.3681647"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681647","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681647","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5111746596","display_name":"Y. Su","orcid":null},"institutions":[{"id":"https://openalex.org/I75390827","display_name":"Beijing University of Chemical Technology","ror":"https://ror.org/00df5yc52","country_code":"CN","type":"education","lineage":["https://openalex.org/I75390827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuhang Su","raw_affiliation_strings":["Beijing University of Chemical Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-3957-5727","affiliations":[{"raw_affiliation_string":"Beijing University of Chemical Technology, Beijing, China","institution_ids":["https://openalex.org/I75390827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100727076","display_name":"Wei Hu","orcid":"https://orcid.org/0000-0001-5320-6086"},"institutions":[{"id":"https://openalex.org/I75390827","display_name":"Beijing University of Chemical Technology","ror":"https://ror.org/00df5yc52","country_code":"CN","type":"education","lineage":["https://openalex.org/I75390827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Hu","raw_affiliation_strings":["Beijing Univeristy of Chemical Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5320-6086","affiliations":[{"raw_affiliation_string":"Beijing Univeristy of Chemical Technology, Beijing, China","institution_ids":["https://openalex.org/I75390827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100690860","display_name":"Fan Zhang","orcid":"https://orcid.org/0000-0002-2058-2373"},"institutions":[{"id":"https://openalex.org/I75390827","display_name":"Beijing University of Chemical Technology","ror":"https://ror.org/00df5yc52","country_code":"CN","type":"education","lineage":["https://openalex.org/I75390827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Zhang","raw_affiliation_strings":["Beijing University of Chemical Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2058-2373","affiliations":[{"raw_affiliation_string":"Beijing University of Chemical Technology, Beijing, China","institution_ids":["https://openalex.org/I75390827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101005666","display_name":"Qiming Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I75390827","display_name":"Beijing University of Chemical Technology","ror":"https://ror.org/00df5yc52","country_code":"CN","type":"education","lineage":["https://openalex.org/I75390827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiming Xu","raw_affiliation_strings":["Beijing University of Chemical Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-0416-1922","affiliations":[{"raw_affiliation_string":"Beijing University of Chemical Technology, Beijing, China","institution_ids":["https://openalex.org/I75390827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5111746596"],"corresponding_institution_ids":["https://openalex.org/I75390827"],"apc_list":null,"apc_paid":null,"fwci":0.3288,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55987913,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"9544","last_page":"9553"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/embedding","display_name":"Embedding","score":0.8600455522537231},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6806255578994751},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6488938331604004},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42914456129074097},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37928858399391174}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8600455522537231},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6806255578994751},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6488938331604004},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42914456129074097},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37928858399391174},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681647","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681647","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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":45,"referenced_works":["https://openalex.org/W83334756","https://openalex.org/W2047411082","https://openalex.org/W2063844407","https://openalex.org/W2076694837","https://openalex.org/W2106053110","https://openalex.org/W2131774270","https://openalex.org/W2194775991","https://openalex.org/W2334757619","https://openalex.org/W2605102252","https://openalex.org/W2609575245","https://openalex.org/W2784163702","https://openalex.org/W2896276533","https://openalex.org/W2962898354","https://openalex.org/W2963026686","https://openalex.org/W2963350250","https://openalex.org/W2963446712","https://openalex.org/W2963466847","https://openalex.org/W2963988212","https://openalex.org/W2964287480","https://openalex.org/W2965178495","https://openalex.org/W2969985801","https://openalex.org/W2991234496","https://openalex.org/W2991642706","https://openalex.org/W2996266053","https://openalex.org/W2998702515","https://openalex.org/W3015666964","https://openalex.org/W3016629994","https://openalex.org/W3017057111","https://openalex.org/W3101227480","https://openalex.org/W3103152812","https://openalex.org/W3138516171","https://openalex.org/W3160719641","https://openalex.org/W3161928252","https://openalex.org/W3162391496","https://openalex.org/W3162472933","https://openalex.org/W3163379884","https://openalex.org/W3205091761","https://openalex.org/W4220931296","https://openalex.org/W4221161255","https://openalex.org/W4224920338","https://openalex.org/W4225565607","https://openalex.org/W4372266723","https://openalex.org/W4384643806","https://openalex.org/W4390872433","https://openalex.org/W6603388714"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2081900870","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890"],"abstract_inverted_index":{"Audio":[0],"Identification":[1],"aims":[2,87],"to":[3,27,58,88,127],"precisely":[4],"retrieve":[5],"exact":[6],"matches":[7],"from":[8],"a":[9,14,60,82,96,152],"vast":[10],"music":[11,29,61],"repository":[12],"through":[13,95],"query":[15],"audio":[16,30,115,159],"snippet.":[17],"The":[18,143],"need":[19],"for":[20,155],"specificity":[21],"and":[22,47,86,99,140,157],"granularity":[23],"has":[24],"traditionally":[25],"led":[26],"representing":[28],"using":[31],"numerous":[32],"short":[33],"fixed-duration":[34],"overlapped":[35],"segment/shingle":[36],"features":[37],"in":[38],"fingerprinting":[39,42,84,130],"approaches.":[40],"However,":[41],"imposes":[43],"constraints":[44],"on":[45,81],"scalability":[46],"efficiency,":[48],"as":[49,93,151],"hundreds":[50],"or":[51],"even":[52],"thousands":[53],"of":[54,108,137,146],"embeddings":[55,94,110],"are":[56],"generated":[57,109],"represent":[59,89],"audio.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66],"present":[67],"an":[68],"innovative":[69],"self-supervised":[70],"approach":[71,131,148],"called":[72],"Angular":[73],"Margin":[74],"Guided":[75],"Embedding":[76],"(AMG-Embedding).":[77],"AMG-Embedding":[78,103,122],"is":[79],"built":[80],"traditional":[83],"encoder":[85],"variable-duration":[90],"non-overlapped":[91],"segments":[92],"two-stage":[97],"embedding":[98],"class-level":[100],"learning":[101],"process.":[102],"significantly":[104],"reduces":[105],"the":[106,128],"number":[107],"while":[111,132],"achieving":[112],"high-specific":[113],"fragment-level":[114],"identification":[116,160],"simultaneously.":[117],"Experimental":[118],"results":[119],"demonstrate":[120],"that":[121],"achieves":[123],"retrieval":[124,141],"accuracy":[125],"comparable":[126],"based":[129],"consuming":[133],"less":[134],"than":[135],"1/10th":[136],"its":[138],"storage":[139],"time.":[142],"efficiency":[144],"gains":[145],"our":[147],"position":[149],"it":[150],"promising":[153],"solution":[154],"scalable":[156],"efficient":[158],"systems.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}