{"id":"https://openalex.org/W4392903770","doi":"https://doi.org/10.1109/icassp48485.2024.10447999","title":"TF-SepNet: An Efficient 1D Kernel Design in Cnns for Low-Complexity Acoustic Scene Classification","display_name":"TF-SepNet: An Efficient 1D Kernel Design in Cnns for Low-Complexity Acoustic Scene Classification","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903770","doi":"https://doi.org/10.1109/icassp48485.2024.10447999"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5114137000","display_name":"Yiqiang Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiqiang Cai","raw_affiliation_strings":["Xi'an Jiaotong-Liverpool University,School of Advanced Technology,Suzhou,China","School of Advanced Technology, Xi'an Jiaotong-Liverpool University, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong-Liverpool University,School of Advanced Technology,Suzhou,China","institution_ids":["https://openalex.org/I69356397"]},{"raw_affiliation_string":"School of Advanced Technology, Xi'an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031949106","display_name":"Peihong Zhang","orcid":"https://orcid.org/0000-0002-0836-316X"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peihong Zhang","raw_affiliation_strings":["Xi'an Jiaotong-Liverpool University,School of Advanced Technology,Suzhou,China","School of Advanced Technology, Xi'an Jiaotong-Liverpool University, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong-Liverpool University,School of Advanced Technology,Suzhou,China","institution_ids":["https://openalex.org/I69356397"]},{"raw_affiliation_string":"School of Advanced Technology, Xi'an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024084275","display_name":"Shengchen Li","orcid":"https://orcid.org/0000-0002-2488-298X"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengchen Li","raw_affiliation_strings":["Xi'an Jiaotong-Liverpool University,School of Advanced Technology,Suzhou,China","School of Advanced Technology, Xi'an Jiaotong-Liverpool University, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong-Liverpool University,School of Advanced Technology,Suzhou,China","institution_ids":["https://openalex.org/I69356397"]},{"raw_affiliation_string":"School of Advanced Technology, Xi'an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5114137000"],"corresponding_institution_ids":["https://openalex.org/I69356397"],"apc_list":null,"apc_paid":null,"fwci":3.2433,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.92519956,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"821","last_page":"825"},"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":0.9994999766349792,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9876999855041504,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7894978523254395},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7362452149391174},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6746293306350708},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6510123610496521},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5571305751800537},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5497140288352966},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.5278579592704773},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4818890690803528},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47225135564804077},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4611656069755554},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3503949046134949},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.24594339728355408},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07772251963615417}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7894978523254395},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7362452149391174},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6746293306350708},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6510123610496521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5571305751800537},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5497140288352966},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.5278579592704773},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4818890690803528},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47225135564804077},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4611656069755554},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3503949046134949},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.24594339728355408},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07772251963615417},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7608752429","display_name":null,"funder_award_id":"Talent","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8527798790","display_name":null,"funder_award_id":"62001038","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2103235956","https://openalex.org/W2622263826","https://openalex.org/W2949846184","https://openalex.org/W2963125010","https://openalex.org/W2980792518","https://openalex.org/W2982415754","https://openalex.org/W3012504141","https://openalex.org/W3097327166","https://openalex.org/W3196496149","https://openalex.org/W3209152703","https://openalex.org/W4226334005","https://openalex.org/W4282044900","https://openalex.org/W4293776874","https://openalex.org/W4307823382","https://openalex.org/W6726497184","https://openalex.org/W6729983426","https://openalex.org/W6739622702","https://openalex.org/W6752516136"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W4321487865","https://openalex.org/W4313906399","https://openalex.org/W4239306820","https://openalex.org/W1820289435","https://openalex.org/W1927135183","https://openalex.org/W2890436937","https://openalex.org/W1596300871","https://openalex.org/W3090190000","https://openalex.org/W1921971915"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"focus":[2],"on":[3],"developing":[4],"efficient":[5,37],"systems":[6],"for":[7],"acoustic":[8],"scene":[9],"classification":[10],"(ASC)":[11],"using":[12,29,108],"convolutional":[13],"neural":[14],"networks":[15],"(CNNs),":[16],"which":[17,146],"typically":[18],"consist":[19],"of":[20,28,48,86],"consecutive":[21,128],"kernels.":[22,129],"This":[23],"paper":[24],"highlights":[25],"the":[26,45,59,63,71,83,87,101,109,135],"benefits":[27],"separate":[30,72,136],"kernels":[31,98,137],"as":[32],"a":[33,54,140],"more":[34,151],"powerful":[35],"and":[36,65,79],"design":[38],"approach":[39],"in":[40],"ASC":[41],"tasks.":[42],"Inspired":[43],"by":[44,77],"time-frequency":[46,152],"nature":[47],"audio":[49],"signals,":[50],"we":[51],"propose":[52],"TF-SepNet,":[53],"CNN":[55],"architecture":[56],"that":[57,121,126,134],"separates":[58],"feature":[60],"processing":[61],"along":[62],"time":[64],"frequency":[66],"dimensions.":[67],"Features":[68],"resulted":[69],"from":[70],"paths":[73],"are":[74],"then":[75],"merged":[76],"channels":[78],"directly":[80],"forwarded":[81],"to":[82,99,139,149],"classifier.":[84],"Instead":[85],"conventional":[88],"two":[89],"dimensional":[90,96],"(2D)":[91],"kernel,":[92],"TF-SepNet":[93,122,148],"incorporates":[94],"one":[95],"(1D)":[97],"reduce":[100],"computational":[102],"costs.":[103],"Experiments":[104],"have":[105],"been":[106],"conducted":[107],"TAU":[110],"Urban":[111],"Acoustic":[112],"Scene":[113],"2022":[114],"Mobile":[115],"development":[116],"dataset.":[117],"The":[118],"results":[119],"show":[120],"outperforms":[123],"similar":[124],"state-of-the-arts":[125],"use":[127],"A":[130],"further":[131],"investigation":[132],"reveals":[133],"lead":[138],"larger":[141],"effective":[142],"receptive":[143],"field":[144],"(ERF),":[145],"enables":[147],"capture":[150],"features.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}