{"id":"https://openalex.org/W4226442948","doi":"https://doi.org/10.1109/icassp43922.2022.9746312","title":"HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection","display_name":"HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4226442948","doi":"https://doi.org/10.1109/icassp43922.2022.9746312"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746312","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-04766512","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100451980","display_name":"Ke Chen","orcid":"https://orcid.org/0000-0001-8357-3741"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ke Chen","raw_affiliation_strings":["University of California San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091528537","display_name":"Xingjian Du","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingjian Du","raw_affiliation_strings":["Bytedance Inc.,AI Lab","AI Lab, Bytedance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Inc.,AI Lab","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"AI Lab, Bytedance Inc","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100934338","display_name":"Bilei Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bilei Zhu","raw_affiliation_strings":["Bytedance Inc.,AI Lab","AI Lab, Bytedance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Inc.,AI Lab","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"AI Lab, Bytedance Inc","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110851569","display_name":"Zejun Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zejun Ma","raw_affiliation_strings":["Bytedance Inc.,AI Lab","AI Lab, Bytedance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Inc.,AI Lab","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"AI Lab, Bytedance Inc","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017455302","display_name":"Taylor Berg-Kirkpatrick","orcid":"https://orcid.org/0000-0002-1283-4075"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taylor Berg-Kirkpatrick","raw_affiliation_strings":["University of California San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042278809","display_name":"Shlomo Dubnov","orcid":"https://orcid.org/0000-0003-0222-1125"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shlomo Dubnov","raw_affiliation_strings":["University of California San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":257,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"646","last_page":"650"},"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":0.9976000189781189,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9973999857902527,"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":0.7461944222450256},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5448252558708191},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5250042676925659},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5064572095870972},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4914780855178833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3289238214492798},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32311975955963135},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2007644772529602},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10967296361923218},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10922333598136902},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.10264432430267334}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7461944222450256},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5448252558708191},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5250042676925659},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5064572095870972},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4914780855178833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3289238214492798},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32311975955963135},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2007644772529602},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10967296361923218},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10922333598136902},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.10264432430267334},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746312","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04766512v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04766512","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2022, Singapore, France. pp.646-650, ⟨10.1109/ICASSP43922.2022.9746312⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04766512v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04766512","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2022, Singapore, France. pp.646-650, ⟨10.1109/ICASSP43922.2022.9746312⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1975817689","https://openalex.org/W2016215128","https://openalex.org/W2052666245","https://openalex.org/W2108598243","https://openalex.org/W2593116425","https://openalex.org/W2765407302","https://openalex.org/W2797583228","https://openalex.org/W2936774411","https://openalex.org/W2955425717","https://openalex.org/W2963610932","https://openalex.org/W2973109987","https://openalex.org/W3005441616","https://openalex.org/W3006275583","https://openalex.org/W3047386385","https://openalex.org/W3047453285","https://openalex.org/W3094550259","https://openalex.org/W3101039626","https://openalex.org/W3119913666","https://openalex.org/W3138516171","https://openalex.org/W3142837074","https://openalex.org/W3162999565","https://openalex.org/W3163379884","https://openalex.org/W3170874841","https://openalex.org/W3178592608","https://openalex.org/W3196974791","https://openalex.org/W3197827948","https://openalex.org/W3198035615","https://openalex.org/W3205743929","https://openalex.org/W4226151502","https://openalex.org/W4286582832","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6745136726","https://openalex.org/W6750665317","https://openalex.org/W6762718338","https://openalex.org/W6781423933","https://openalex.org/W6781553146","https://openalex.org/W6788135285","https://openalex.org/W6840046036"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2997152889","https://openalex.org/W4285141722","https://openalex.org/W4304700937"],"abstract_inverted_index":{"Audio":[0],"classification":[1,115],"is":[2,80],"an":[3,64],"important":[4],"task":[5],"of":[6,113,159,173],"mapping":[7],"audio":[8,29,55,65,100,114,162],"samples":[9],"into":[10,91],"their":[11],"corresponding":[12],"labels.":[13],"Recently,":[14],"the":[15,51,73,96,99,129,144,160,167],"transformer":[16,66],"model":[17,74,97,153],"with":[18,67,83],"self-attention":[19],"mechanisms":[20],"has":[21],"been":[22],"adopted":[23],"in":[24,54,105,140],"this":[25],"field.":[26],"However,":[27],"existing":[28],"transformers":[30],"require":[31],"large":[32],"GPU":[33],"memories":[34],"and":[35,76,125,127,155,170],"long":[36],"training":[37,77,157],"time,":[38],"meanwhile":[39],"relying":[40],"on":[41,110,123,131],"pretrained":[42],"vision":[43],"models":[44],"to":[45,71,87],"achieve":[46],"high":[47,168,171],"performance,":[48],"which":[49],"limits":[50],"model\u2019s":[52],"scalability":[53],"tasks.":[56],"To":[57],"combat":[58],"these":[59],"problems,":[60],"we":[61],"introduce":[62],"HTS-AT:":[63],"a":[68,84],"hierarchical":[69],"structure":[70],"reduce":[72],"size":[75],"time.":[78],"It":[79,135],"further":[81],"combined":[82],"token-semantic":[85],"module":[86],"map":[88],"final":[89],"outputs":[90],"class":[92],"featuremaps,":[93],"thus":[94],"enabling":[95],"for":[98],"event":[101,141],"detection":[102],"(i.e.":[103],"localization":[104,142],"time).":[106],"We":[107],"evaluate":[108],"HTS-AT":[109,149],"three":[111],"datasets":[112],"where":[116],"it":[117],"achieves":[118,137],"new":[119],"state-of-the-art":[120],"(SOTA)":[121],"results":[122,165],"AudioSet":[124],"ESC50,":[126],"equals":[128],"SOTA":[130],"Speech":[132],"Command":[133],"V2.":[134],"also":[136],"better":[138],"performance":[139,169],"than":[143],"previous":[145,161],"CNN-based":[146],"models.":[147],"Moreover,":[148],"requires":[150],"only":[151],"35%":[152],"parameters":[154],"15%":[156],"time":[158],"transformer.":[163],"These":[164],"demonstrate":[166],"efficiency":[172],"HTS-AT.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":32},{"year":2025,"cited_by_count":91},{"year":2024,"cited_by_count":88},{"year":2023,"cited_by_count":41},{"year":2022,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}