{"id":"https://openalex.org/W4416799780","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249247","title":"PALGAN: A Joint Optimization-Based Preprocessing method for Speech Restoration in Parametric Array Loudspeakers","display_name":"PALGAN: A Joint Optimization-Based Preprocessing method for Speech Restoration in Parametric Array Loudspeakers","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799780","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249247"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249247","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5101782485","display_name":"Wenyao Ma","orcid":"https://orcid.org/0009-0005-0695-0925"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyao Ma","raw_affiliation_strings":["Institute of Acoustics, Chinese Academy of Sciences,Laboratory of Noise and Audio Research,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy of Sciences,Laboratory of Noise and Audio Research,Beijing,China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030686595","display_name":"Jun Yang","orcid":"https://orcid.org/0000-0003-1652-0054"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yang","raw_affiliation_strings":["Institute of Acoustics, Chinese Academy of Sciences,Laboratory of Noise and Audio Research,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy of Sciences,Laboratory of Noise and Audio Research,Beijing,China","institution_ids":["https://openalex.org/I4210099069"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210099069"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.387717,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1140","last_page":"1145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9124000072479248,"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":0.9124000072479248,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.025100000202655792,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.023000000044703484,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7425000071525574},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5881999731063843},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.5763000249862671},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5540000200271606},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4999000132083893},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.46650001406669617},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4388999938964844},{"id":"https://openalex.org/keywords/baseband","display_name":"Baseband","score":0.41350001096725464},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.4050999879837036},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.38589999079704285}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.754800021648407},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7425000071525574},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5881999731063843},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.5763000249862671},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5745000243186951},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5540000200271606},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4999000132083893},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.46650001406669617},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4388999938964844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4253000020980835},{"id":"https://openalex.org/C65165936","wikidata":"https://www.wikidata.org/wiki/Q575784","display_name":"Baseband","level":3,"score":0.41350001096725464},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.4050999879837036},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.38589999079704285},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38019999861717224},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.3783999979496002},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.31470000743865967},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C207912722","wikidata":"https://www.wikidata.org/wiki/Q1259123","display_name":"Signal generator","level":3,"score":0.3138999938964844},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.30149999260902405},{"id":"https://openalex.org/C173413354","wikidata":"https://www.wikidata.org/wiki/Q7049470","display_name":"Nonlinear distortion","level":4,"score":0.29739999771118164},{"id":"https://openalex.org/C2780909371","wikidata":"https://www.wikidata.org/wiki/Q4801092","display_name":"Artificial noise","level":4,"score":0.2937000095844269},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.28290000557899475},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2694000005722046},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.25540000200271606},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249247","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":32,"referenced_works":["https://openalex.org/W1547461227","https://openalex.org/W1552314771","https://openalex.org/W1964259028","https://openalex.org/W2031633662","https://openalex.org/W2044819698","https://openalex.org/W2107860279","https://openalex.org/W2112861662","https://openalex.org/W2122545463","https://openalex.org/W2127559196","https://openalex.org/W2127851351","https://openalex.org/W2128658463","https://openalex.org/W2143291908","https://openalex.org/W2396281413","https://openalex.org/W2516001803","https://openalex.org/W2593414223","https://openalex.org/W2973044449","https://openalex.org/W3015338123","https://openalex.org/W3134076923","https://openalex.org/W3160553598","https://openalex.org/W3162493033","https://openalex.org/W3191448984","https://openalex.org/W3196475561","https://openalex.org/W3197042120","https://openalex.org/W4206537410","https://openalex.org/W4225302959","https://openalex.org/W4225956675","https://openalex.org/W4230637137","https://openalex.org/W4385756463","https://openalex.org/W4407406952","https://openalex.org/W4408352708","https://openalex.org/W4408353733","https://openalex.org/W4408709579"],"related_works":[],"abstract_inverted_index":{"The":[0,122],"parametric":[1],"array":[2],"loudspeaker":[3],"(PAL)":[4],"inherently":[5],"introduces":[6],"baseband":[7],"distortions":[8],"in":[9,18,59,64],"directional":[10],"sound":[11],"applications":[12],"due":[13],"to":[14,28,105,113,128,169],"the":[15,49,53,60,87,91,101,108,114,130,136,150,170],"nonlinear":[16],"process":[17,89,95,116],"air.":[19],"Recently,":[20],"a":[21,37,43,72,78,119,125,140],"two-stage":[22],"DNNbased":[23],"framework":[24],"has":[25],"been":[26],"used":[27],"generate":[29],"preprocessed":[30,137],"signals":[31],"for":[32],"distortion-free":[33],"speech":[34,174],"restoration,":[35],"where":[36],"preprocessing":[38,54,92],"network":[39,55,82],"is":[40,98],"cascaded":[41],"with":[42,159],"frozen":[44],"forward":[45,120],"model":[46],"that":[47,149],"estimates":[48],"PAL":[50,88,115],"system.":[51],"However,":[52],"can":[56],"exploit":[57],"weaknesses":[58],"fixed":[61],"model,":[62],"resulting":[63],"adversarial":[65,81],"outputs.":[66],"To":[67],"address":[68],"this,":[69],"we":[70],"propose":[71],"joint":[73],"optimization":[74],"strategy":[75],"based":[76],"on":[77],"PAL-driven":[79],"generative":[80],"(PALGAN),":[83],"which":[84],"simultaneously":[85],"learns":[86],"and":[90,132,145,173],"module.":[93],"A":[94],"discrimination":[96],"mechanism":[97],"incorporated":[99],"into":[100],"discriminator,":[102],"enabling":[103],"it":[104],"determine":[106],"whether":[107],"input":[109],"signal":[110,138],"pair":[111],"conform":[112],"while":[117],"acquiring":[118],"model.":[121],"generator":[123],"uses":[124],"causal":[126],"TF-GridNet":[127],"estimate":[129],"real":[131],"imaginary":[133],"parts":[134],"of":[135],"via":[139],"time-frequency":[141],"band-split":[142],"mechanism.":[143],"Simulated":[144],"real-world":[146],"experiments":[147],"demonstrate":[148],"proposed":[151],"method":[152],"achieves":[153],"competitive":[154],"reconstruction":[155],"performance":[156],"when":[157],"compared":[158],"existing":[160],"methods":[161],"across":[162],"various":[163],"objective":[164],"metrics<sup":[165],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[166],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>For":[167],"access":[168],"source":[171],"code":[172],"samples,":[175],"please":[176],"visit:":[177],"https://github.com/MWY0615/PALGAN..":[178]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}