{"id":"https://openalex.org/W4391021628","doi":"https://doi.org/10.1109/asru57964.2023.10389687","title":"Improving Speech Enhancement Using Audio Tagging Knowledge From Pre-Trained Representations and Multi-Task Learning","display_name":"Improving Speech Enhancement Using Audio Tagging Knowledge From Pre-Trained Representations and Multi-Task Learning","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021628","doi":"https://doi.org/10.1109/asru57964.2023.10389687"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5025504424","display_name":"Shaoxiong Lin","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":"Shaoxiong Lin","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460223","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0002-9583-0722"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China","Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"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"]},{"id":"https://openalex.org/I4210125878","display_name":"Suzhou Research Institute","ror":"https://ror.org/03ebk0c60","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210125878"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","Suzhou Institute of Artificial Intelligence, Shanghai Jiao Tong University, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Suzhou Institute of Artificial Intelligence, Shanghai Jiao Tong University, Suzhou, China","institution_ids":["https://openalex.org/I183067930","https://openalex.org/I4210125878"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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":0.998199999332428,"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":0.9952999949455261,"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/computer-science","display_name":"Computer science","score":0.8225327730178833},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6537137031555176},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6450244784355164},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5465922951698303},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5280160307884216},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5039963126182556},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44103553891181946},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.42454105615615845},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4220356047153473},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.41121822595596313},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3823891878128052},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.38221800327301025},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3590173125267029},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.3495669960975647}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8225327730178833},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6537137031555176},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6450244784355164},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5465922951698303},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5280160307884216},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5039963126182556},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44103553891181946},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.42454105615615845},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4220356047153473},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.41121822595596313},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3823891878128052},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.38221800327301025},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3590173125267029},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3495669960975647},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7200000286102295,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1964538581","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2291877678","https://openalex.org/W2408688265","https://openalex.org/W2593116425","https://openalex.org/W2890820256","https://openalex.org/W2952218014","https://openalex.org/W2959214850","https://openalex.org/W2963045393","https://openalex.org/W2963082324","https://openalex.org/W2963103134","https://openalex.org/W2964207404","https://openalex.org/W2998161426","https://openalex.org/W3015199127","https://openalex.org/W3094550259","https://openalex.org/W3096408984","https://openalex.org/W3096643087","https://openalex.org/W3099330747","https://openalex.org/W3113290170","https://openalex.org/W3161140524","https://openalex.org/W3161950572","https://openalex.org/W3162534564","https://openalex.org/W3197627016","https://openalex.org/W3198543387","https://openalex.org/W3203119473","https://openalex.org/W3206706278","https://openalex.org/W3206809722","https://openalex.org/W4224919629","https://openalex.org/W4225310539","https://openalex.org/W4226185896","https://openalex.org/W4283741319","https://openalex.org/W4289665794","https://openalex.org/W4310873168","https://openalex.org/W4319586676","https://openalex.org/W4319862644","https://openalex.org/W4372260051","https://openalex.org/W4372270323","https://openalex.org/W4372346771","https://openalex.org/W6745995898","https://openalex.org/W6802205285","https://openalex.org/W6838901088"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W2157598242","https://openalex.org/W27741130","https://openalex.org/W1969715806","https://openalex.org/W2020966186","https://openalex.org/W2784103281","https://openalex.org/W1620668332","https://openalex.org/W2175408845","https://openalex.org/W1479881079","https://openalex.org/W1503775422"],"abstract_inverted_index":{"In":[0,36],"deep-learning-based":[1],"speech":[2,21,25],"enhancement":[3],"(SE),":[4],"an":[5,39],"audio-knowledge-ignorant":[6],"approach":[7,41,116],"is":[8,42,73],"often":[9],"used,":[10],"which":[11,47],"estimates":[12],"a":[13],"denoising":[14],"model":[15,111],"to":[16,44,55,118],"transform":[17],"the":[18,28,33,50,57,62,69,102,106,114,122],"noisy":[19],"input":[20,78],"into":[22],"clean":[23],"output":[24],"without":[26],"understanding":[27],"audio":[29,53,66,70,83,92,109],"events":[30],"that":[31,113],"constitute":[32],"background":[34,58],"noises.":[35,59],"this":[37],"paper,":[38],"audio-knowledge-aware":[40],"proposed":[43,115],"improve":[45],"SE,":[46],"explicitly":[48],"leverages":[49],"knowledge":[51,72],"from":[52,87],"taggings":[54],"understand":[56],"Based":[60],"on":[61,101],"recent":[63],"progress":[64],"in":[65,121],"pattern":[67],"analysis,":[68],"tagging":[71,84,110],"obtained":[74],"using":[75],"either":[76],"additional":[77],"representations":[79],"extracted":[80],"by":[81],"pre-trained":[82,107],"models,":[85],"or":[86,95],"multi-task":[88],"learning":[89],"with":[90],"extra":[91],"event":[93],"classification":[94],"regression":[96],"tasks.":[97],"Experimental":[98],"results":[99],"based":[100],"DNS-2020":[103],"dataset":[104],"and":[105,125],"Wavegram-Logmel-CNN":[108],"show":[112],"leads":[117],"considerable":[119],"improvements":[120],"STOI,":[123],"SDR,":[124],"SI-SNR":[126],"metrics.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-27T08:26:11.824852","created_date":"2025-10-10T00:00:00"}