{"id":"https://openalex.org/W4225327445","doi":"https://doi.org/10.1109/icassp43922.2022.9747722","title":"Category-Adapted Sound Event Enhancement with Weakly Labeled Data","display_name":"Category-Adapted Sound Event Enhancement with Weakly Labeled Data","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225327445","doi":"https://doi.org/10.1109/icassp43922.2022.9747722"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747722","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747722","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":"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/A5002348751","display_name":"Guangwei Li","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangwei Li","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence X-LANCE Lab,Department of Computer Science and Engineering AI Institute,Shanghai,China","Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence X-LANCE Lab,Department of Computer Science and Engineering AI Institute,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025827045","display_name":"Xuenan Xu","orcid":"https://orcid.org/0000-0001-8718-1278"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuenan Xu","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence X-LANCE Lab,Department of Computer Science and Engineering AI Institute,Shanghai,China","Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence X-LANCE Lab,Department of Computer Science and Engineering AI Institute,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080154283","display_name":"Heinrich Dinkel","orcid":"https://orcid.org/0000-0003-4330-8980"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heinrich Dinkel","raw_affiliation_strings":["Xiaomi Corporation,Beijing,China","Xiaomi Corporation, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081865665","display_name":"Mengyue Wu","orcid":"https://orcid.org/0000-0002-5599-8707"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyue Wu","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence X-LANCE Lab,Department of Computer Science and Engineering AI Institute,Shanghai,China","Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence X-LANCE Lab,Department of Computer Science and Engineering AI Institute,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence X-LANCE Lab,Department of Computer Science and Engineering AI Institute,Shanghai,China","Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence X-LANCE Lab,Department of Computer Science and Engineering AI Institute,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.363,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.47560592,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"851","last_page":"855"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9980999827384949,"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/event","display_name":"Event (particle physics)","score":0.6700320839881897},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6338685154914856},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6250443458557129},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6211385726928711},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4922298491001129},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.44243016839027405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2887287139892578},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.27831923961639404},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.13230407238006592}],"concepts":[{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6700320839881897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6338685154914856},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6250443458557129},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6211385726928711},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4922298491001129},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.44243016839027405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2887287139892578},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.27831923961639404},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.13230407238006592},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747722","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747722","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6600000262260437,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1897240248","https://openalex.org/W1901129140","https://openalex.org/W2024490156","https://openalex.org/W2044893557","https://openalex.org/W2113131123","https://openalex.org/W2128653836","https://openalex.org/W2219249508","https://openalex.org/W2405774341","https://openalex.org/W2593116425","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W2963103134","https://openalex.org/W2963341071","https://openalex.org/W2963610932","https://openalex.org/W2972411915","https://openalex.org/W2972541922","https://openalex.org/W3004910802","https://openalex.org/W3016059657","https://openalex.org/W3093839391","https://openalex.org/W3095263845","https://openalex.org/W3099330747","https://openalex.org/W3124216180","https://openalex.org/W3125993195","https://openalex.org/W3151851237","https://openalex.org/W3197734536","https://openalex.org/W4295312788","https://openalex.org/W6639824700","https://openalex.org/W6688816777","https://openalex.org/W6735429107","https://openalex.org/W6766978945","https://openalex.org/W6776165281","https://openalex.org/W6784499681"],"related_works":["https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W2909888262","https://openalex.org/W2025747832","https://openalex.org/W3020957235","https://openalex.org/W2056769785","https://openalex.org/W1630865680","https://openalex.org/W611303608","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"Previous":[0],"audio":[1],"enhancement":[2,32,62,108,139],"training":[3],"usually":[4],"requires":[5,155],"clean":[6,18,156],"signals":[7],"with":[8,100,118],"additive":[9],"noises;":[10],"hence":[11],"commonly":[12],"focuses":[13],"on":[14,63,95,122],"speech":[15,19,123],"enhancement,":[16],"where":[17,68],"is":[20,93],"easy":[21],"to":[22,44,60,74,86,103,150],"access.":[23],"This":[24],"paper":[25],"goes":[26],"beyond":[27],"a":[28,35,51,57,82,101],"broader":[29],"sound":[30,40,53,66,77,90,98],"event":[31,41],"by":[33,81],"using":[34],"weakly":[36,106,143],"supervised":[37,107,144],"approach":[38],"via":[39],"detection":[42],"(SED)":[43],"approximate":[45],"the":[46,72,88,151],"location":[47],"and":[48,79,105,129,146],"presence":[49],"of":[50,135],"specific":[52],"event.":[54],"We":[55],"propose":[56],"category-adapted":[58],"system":[59],"enable":[61],"any":[64],"selected":[65],"category,":[67],"we":[69],"first":[70],"familiarize":[71],"model":[73],"all":[75],"common":[76,97],"classes":[78],"followed":[80],"category-specific":[83],"fine-tune":[84],"procedure":[85],"enhance":[87],"targeted":[89],"class.":[91],"Evaluation":[92],"conducted":[94],"ten":[96],"classes,":[99],"comparison":[102],"traditional":[104],"methods.":[109],"Results":[110],"indicate":[111],"an":[112],"average":[113],"2.86":[114],"dB":[115],"SDR":[116],"increase,":[117],"more":[119],"significant":[120],"improvement":[121],"(9.15":[124],"dB),":[125,128],"music":[126],"(5.01":[127],"typewriter":[130],"(3.68":[131],"dB)":[132],"under":[133],"SNR":[134],"0":[136],"dB.":[137],"All":[138],"metrics":[140],"outperform":[141],"previous":[142],"methods":[145],"achieve":[147],"comparable":[148],"results":[149],"state-of-the-art":[152],"method":[153],"that":[154],"signals.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}