{"id":"https://openalex.org/W4372267124","doi":"https://doi.org/10.1109/icassp49357.2023.10096787","title":"CAT: Causal Audio Transformer for Audio Classification","display_name":"CAT: Causal Audio Transformer for Audio Classification","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372267124","doi":"https://doi.org/10.1109/icassp49357.2023.10096787"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096787","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096787","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5100455531","display_name":"Xiaoyu Liu","orcid":"https://orcid.org/0009-0005-6402-3855"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoyu Liu","raw_affiliation_strings":["University of Maryland,College Park","University of Maryland, College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103969791","display_name":"Lu Hanlin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hanlin Lu","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025459071","display_name":"Jianbo Yuan","orcid":"https://orcid.org/0000-0002-8905-7438"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianbo Yuan","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100406104","display_name":"Xinyu Li","orcid":"https://orcid.org/0000-0002-3730-0360"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinyu Li","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9692999720573425,"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/interpretability","display_name":"Interpretability","score":0.7873684167861938},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7371147274971008},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5641270875930786},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5029959082603455},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4845947027206421},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46920934319496155},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4175064265727997},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.41610321402549744},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4135613441467285},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39836347103118896},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.350995808839798},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12860208749771118},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.10671675205230713}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7873684167861938},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7371147274971008},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5641270875930786},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5029959082603455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4845947027206421},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46920934319496155},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4175064265727997},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.41610321402549744},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4135613441467285},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39836347103118896},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.350995808839798},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12860208749771118},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.10671675205230713},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096787","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096787","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2143891888","https://openalex.org/W2593116425","https://openalex.org/W2745357708","https://openalex.org/W2765407302","https://openalex.org/W2766607545","https://openalex.org/W2768188490","https://openalex.org/W2962793908","https://openalex.org/W2963173418","https://openalex.org/W3094502228","https://openalex.org/W3094550259","https://openalex.org/W3118608800","https://openalex.org/W3138516171","https://openalex.org/W3161026535","https://openalex.org/W3173678936","https://openalex.org/W3173801460","https://openalex.org/W3174906557","https://openalex.org/W3176726917","https://openalex.org/W3196778703","https://openalex.org/W3196974791","https://openalex.org/W3205475937","https://openalex.org/W3205743929","https://openalex.org/W4214516465","https://openalex.org/W4224924125","https://openalex.org/W4226109839","https://openalex.org/W4226442948","https://openalex.org/W4289288178","https://openalex.org/W4372266552","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6745136726","https://openalex.org/W6745930336","https://openalex.org/W6749107692","https://openalex.org/W6755726434","https://openalex.org/W6784333009","https://openalex.org/W6787972765","https://openalex.org/W6797613833","https://openalex.org/W6800694804","https://openalex.org/W6802510933","https://openalex.org/W6810405975","https://openalex.org/W6810706523","https://openalex.org/W6838439425"],"related_works":["https://openalex.org/W2970176078","https://openalex.org/W2289868279","https://openalex.org/W1975359510","https://openalex.org/W2350061705","https://openalex.org/W1496727373","https://openalex.org/W4254699594","https://openalex.org/W2020952589","https://openalex.org/W1526651343","https://openalex.org/W2069094726","https://openalex.org/W2146634268"],"abstract_inverted_index":{"The":[0],"attention-based":[1],"Transformers":[2,33],"have":[3],"been":[4],"increasingly":[5],"applied":[6],"to":[7,18,106],"audio":[8,39,68],"classification":[9,93],"because":[10],"of":[11,52],"their":[12],"global":[13],"receptive":[14],"field":[15],"and":[16,84,98,101],"ability":[17],"handle":[19],"long-term":[20],"dependency.":[21],"However,":[22],"the":[23,31],"existing":[24],"frameworks":[25],"which":[26],"are":[27,34],"mainly":[28],"extended":[29],"from":[30],"Vision":[32],"not":[35],"perfectly":[36],"compatible":[37],"with":[38,60,81],"signals.":[40],"In":[41,70],"this":[42],"paper,":[43],"we":[44,72],"introduce":[45],"a":[46,53,74],"Causal":[47],"Audio":[48],"Transformer":[49],"(CAT)":[50],"consisting":[51],"Multi-Resolution":[54],"Multi-":[55],"Feature":[56],"(MRMF)":[57],"feature":[58],"extraction":[59],"an":[61],"acoustic":[62],"attention":[63],"block":[64],"for":[65],"more":[66],"optimized":[67],"modeling.":[69],"addition,":[71],"propose":[73],"causal":[75],"module":[76],"that":[77],"alleviates":[78],"over-fitting,":[79],"helps":[80],"knowledge":[82],"transfer":[83],"improves":[85],"interpretability.":[86],"CAT":[87],"obtains":[88],"higher":[89],"or":[90],"comparable":[91],"state-of-the-art":[92],"performance":[94],"on":[95],"ESC50,":[96],"AudioSet":[97],"UrbanSound8K":[99],"datasets,":[100],"can":[102],"be":[103],"easily":[104],"generalized":[105],"other":[107],"Transformer-":[108],"based":[109],"models.":[110]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}