{"id":"https://openalex.org/W4387437369","doi":"https://doi.org/10.1109/taslp.2023.3277246","title":"A Physical Model-Based Self-Supervised Learning Method for Signal Enhancement Under Reverberant Environment","display_name":"A Physical Model-Based Self-Supervised Learning Method for Signal Enhancement Under Reverberant Environment","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4387437369","doi":"https://doi.org/10.1109/taslp.2023.3277246"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3277246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3277246","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5100650768","display_name":"Shan Gao","orcid":"https://orcid.org/0000-0003-1189-7776"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shan Gao","raw_affiliation_strings":["Key Laboratory on Machine Perception, (Ministry of Education), School of Intelligence Science and Technology, Speech and Hearing Research Center, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory on Machine Perception, (Ministry of Education), School of Intelligence Science and Technology, Speech and Hearing Research Center, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084685506","display_name":"Xihong Wu","orcid":"https://orcid.org/0009-0004-5236-7469"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xihong Wu","raw_affiliation_strings":["Key Laboratory on Machine Perception, (Ministry of Education), School of Intelligence Science and Technology, Speech and Hearing Research Center, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory on Machine Perception, (Ministry of Education), School of Intelligence Science and Technology, Speech and Hearing Research Center, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103080532","display_name":"Tianshu Qu","orcid":"https://orcid.org/0000-0001-6256-2031"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianshu Qu","raw_affiliation_strings":["Key Laboratory on Machine Perception, (Ministry of Education), School of Intelligence Science and Technology, Speech and Hearing Research Center, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6256-2031","affiliations":[{"raw_affiliation_string":"Key Laboratory on Machine Perception, (Ministry of Education), School of Intelligence Science and Technology, Speech and Hearing Research Center, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100650768"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.5757,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65150108,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"31","issue":null,"first_page":"2100","last_page":"2110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7249723672866821},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.7035927772521973},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.7028151750564575},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5954741835594177},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5629908442497253},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5495478510856628},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5014152526855469},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47870635986328125},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45847088098526},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39380112290382385},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.363768070936203},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3242868185043335},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1862524151802063},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10302236676216125}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7249723672866821},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.7035927772521973},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.7028151750564575},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5954741835594177},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5629908442497253},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5495478510856628},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5014152526855469},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47870635986328125},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45847088098526},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39380112290382385},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.363768070936203},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3242868185043335},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1862524151802063},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10302236676216125},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3277246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3277246","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2401495373","display_name":null,"funder_award_id":"61421062","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3389713118","display_name":null,"funder_award_id":"61175043","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7377807314","display_name":null,"funder_award_id":"22&ZD318","funder_id":"https://openalex.org/F4320335869","funder_display_name":"National Social Science Fund of China"},{"id":"https://openalex.org/G8358198455","display_name":null,"funder_award_id":"2019YFC1408501","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335869","display_name":"National Social Science Fund of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1603978816","https://openalex.org/W1901129140","https://openalex.org/W1980903300","https://openalex.org/W2006129368","https://openalex.org/W2015069270","https://openalex.org/W2061074721","https://openalex.org/W2067295501","https://openalex.org/W2075107327","https://openalex.org/W2096327012","https://openalex.org/W2117678320","https://openalex.org/W2144404214","https://openalex.org/W2149298302","https://openalex.org/W2205176333","https://openalex.org/W2398042854","https://openalex.org/W2494085323","https://openalex.org/W2517616541","https://openalex.org/W2542605056","https://openalex.org/W2609317876","https://openalex.org/W2889335976","https://openalex.org/W2951249128","https://openalex.org/W2962866211","https://openalex.org/W2963941778","https://openalex.org/W2964058413","https://openalex.org/W3015679215","https://openalex.org/W3134202725","https://openalex.org/W3147539069","https://openalex.org/W3160140981","https://openalex.org/W3162341667","https://openalex.org/W3205115292","https://openalex.org/W4210402803","https://openalex.org/W4214652421","https://openalex.org/W4231225162","https://openalex.org/W4245919820","https://openalex.org/W4286750588","https://openalex.org/W4294891356","https://openalex.org/W4297841502","https://openalex.org/W6631190155","https://openalex.org/W6639824700","https://openalex.org/W6840048020"],"related_works":["https://openalex.org/W2357124094","https://openalex.org/W2387399993","https://openalex.org/W2389739210","https://openalex.org/W2348924972","https://openalex.org/W2365736347","https://openalex.org/W2047454415","https://openalex.org/W2070040999","https://openalex.org/W2387293848","https://openalex.org/W2250140200","https://openalex.org/W3121791438"],"abstract_inverted_index":{"In":[0,56,103],"a":[1,26,61,80],"reverberant":[2],"environment,":[3],"interferences":[4],"such":[5],"as":[6],"reflections":[7],"and":[8,113,141,166],"background":[9],"noise":[10],"can":[11,149],"degrade":[12],"the":[13,16,21,33,42,45,70,86,94,97,106,110,114,118,127,130,146,160],"perception":[14],"of":[15,35,44,96,109,117,129],"sound":[17,87],"source":[18,88,154],"signal.":[19],"Although":[20],"DNN-based":[22],"methods":[23],"have":[24],"made":[25],"tremendous":[27],"breakthrough":[28],"in":[29,168],"addressing":[30],"this":[31,57,104],"issue,":[32],"performance":[34],"these":[36],"models":[37],"is":[38],"highly":[39],"dependent":[40],"on":[41,139],"completeness":[43],"training":[46],"dataset,":[47],"which":[48],"will":[49],"limit":[50],"its":[51,164],"generalization":[52],"under":[53,74,100,133],"unknown":[54,75,134],"environments.":[55,170],"paper,":[58],"we":[59],"propose":[60],"physical":[62,83,101],"model-based":[63],"self-supervised":[64],"learning":[65],"(PMSSL)":[66],"method":[67,78,148],"to":[68],"realize":[69],"DNN":[71,98,131],"model":[72,84,90,99,132],"optimization":[73,91],"scenarios.":[76,135],"This":[77],"incorporates":[79],"room":[81],"reverberation":[82,119],"into":[85],"enhancement":[89,156],"process,":[92,105],"realizing":[93],"self-learning":[95],"constraints.":[102],"time-frequency":[107],"characteristics":[108],"input":[111],"signal":[112,155],"spatial":[115],"feature":[116],"environment":[120],"are":[121],"utilized":[122],"for":[123],"parameter":[124],"optimization,":[125],"improving":[126],"adaptability":[128,167],"Experimental":[136],"results":[137,157],"based":[138],"simulated":[140],"measured":[142],"data":[143],"prove":[144],"that":[145],"proposed":[147],"obtain":[150],"much":[151],"more":[152],"accurate":[153],"compared":[158],"with":[159],"pre-trained":[161],"models,":[162],"verifying":[163],"effectiveness":[165],"new":[169]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}