{"id":"https://openalex.org/W4372266156","doi":"https://doi.org/10.1109/icassp49357.2023.10096319","title":"SemanticAC: Semantics-Assisted Framework for Audio Classification","display_name":"SemanticAC: Semantics-Assisted Framework for Audio Classification","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266156","doi":"https://doi.org/10.1109/icassp49357.2023.10096319"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096319","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":"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/A5046633330","display_name":"Yicheng Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yicheng Xiao","raw_affiliation_strings":["Tsinghua University,Tsinghua Shenzhen International Graduate School,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua Shenzhen International Graduate School,China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443132","display_name":"Yue Ma","orcid":"https://orcid.org/0000-0002-0767-9007"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Ma","raw_affiliation_strings":["Tsinghua University,Tsinghua Shenzhen International Graduate School,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua Shenzhen International Graduate School,China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669301","display_name":"Shuyan Li","orcid":"https://orcid.org/0000-0002-5107-0338"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuyan Li","raw_affiliation_strings":["Tsinghua University,Tsinghua Shenzhen International Graduate School,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua Shenzhen International Graduate School,China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102510889","display_name":"Hantao Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hantao Zhou","raw_affiliation_strings":["Tsinghua University,Tsinghua Shenzhen International Graduate School,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua Shenzhen International Graduate School,China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027794673","display_name":"Ran Liao","orcid":"https://orcid.org/0000-0002-3088-2230"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ran Liao","raw_affiliation_strings":["Tsinghua University,Tsinghua Shenzhen International Graduate School,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua Shenzhen International Graduate School,China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100754504","display_name":"Xiu Li","orcid":"https://orcid.org/0000-0003-0403-1923"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiu Li","raw_affiliation_strings":["Tsinghua University,Tsinghua Shenzhen International Graduate School,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua Shenzhen International Graduate School,China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5046633330"],"corresponding_institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.4264,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.81683881,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9965000152587891,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9940000176429749,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8219974637031555},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7881158590316772},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6743504405021667},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.640753984451294},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.5628803372383118},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.524706244468689},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5186866521835327},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5105184316635132},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4972725212574005},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33208340406417847},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3285309076309204},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07991740107536316}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8219974637031555},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7881158590316772},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6743504405021667},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.640753984451294},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.5628803372383118},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.524706244468689},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5186866521835327},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5105184316635132},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4972725212574005},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33208340406417847},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3285309076309204},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07991740107536316},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096319","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2034940213","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2086161653","https://openalex.org/W2593116425","https://openalex.org/W2884585870","https://openalex.org/W2889387262","https://openalex.org/W2963838685","https://openalex.org/W2990408345","https://openalex.org/W3045062880","https://openalex.org/W3094502228","https://openalex.org/W3113823857","https://openalex.org/W3154169693","https://openalex.org/W3166396011","https://openalex.org/W3174906557","https://openalex.org/W3175300676","https://openalex.org/W3176445421","https://openalex.org/W3196974791","https://openalex.org/W3201065055","https://openalex.org/W3214261769","https://openalex.org/W4224920397","https://openalex.org/W4224924125","https://openalex.org/W4226442948","https://openalex.org/W4285606530","https://openalex.org/W4296068596","https://openalex.org/W4310922994","https://openalex.org/W4313018127","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6753412334","https://openalex.org/W6770805772","https://openalex.org/W6776441977","https://openalex.org/W6791353385","https://openalex.org/W6797613833"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W4205302943","https://openalex.org/W2119949815","https://openalex.org/W2561132942","https://openalex.org/W2142795561","https://openalex.org/W3155418658","https://openalex.org/W4243199227","https://openalex.org/W4323929292"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,30,73,90],"propose":[4],"SemanticAC,":[5],"a":[6,32,75,109],"semantics-assisted":[7],"framework":[8],"for":[9,69],"Audio":[10],"Classification":[11],"to":[12,35,78,95,115],"better":[13,70],"leverage":[14],"the":[15,43,80,84,92,98,117,136],"semantic":[16,44,67,81,118],"information.":[17],"Unlike":[18],"conventional":[19],"audio":[20,47,93,106,124,138],"classification":[21,139],"methods":[22],"that":[23,54,130],"treat":[24],"class":[25,102],"labels":[26,40,59,103],"as":[27,114],"discrete":[28],"vectors,":[29],"employ":[31],"language":[33],"model":[34],"extract":[36],"abundant":[37,66],"semantics":[38,99],"from":[39,58,83],"and":[41,49,60,108,127],"optimize":[42],"consistency":[45],"between":[46],"signals":[48,94],"their":[50],"labels.":[51,88],"We":[52],"verify":[53],"simple":[55],"textual":[56],"information":[57,82],"advanced":[61],"pretraining":[62],"models":[63],"enable":[64],"more":[65],"supervision":[68],"performance.":[71],"Specifically,":[72],"design":[74],"text":[76,85],"encoder":[77,107],"capture":[79],"extension":[86],"of":[87,100],"Then":[89],"map":[91],"align":[96],"with":[97],"corresponding":[101],"via":[104],"an":[105],"similarity":[110],"calculation":[111],"module":[112],"so":[113],"enforce":[116],"consistency.":[119],"Extensive":[120],"experiments":[121],"on":[122],"two":[123],"datasets,":[125],"ESC-50":[126],"US8K":[128],"demonstrate":[129],"our":[131],"proposed":[132],"method":[133],"consistently":[134],"outperforms":[135],"compared":[137],"methods.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}