{"id":"https://openalex.org/W4410737797","doi":"https://doi.org/10.1109/access.2025.3573458","title":"Multi-Step Quality-Oriented Training for Cross-Dataset Offline Iterative Speech Enhancement","display_name":"Multi-Step Quality-Oriented Training for Cross-Dataset Offline Iterative Speech Enhancement","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4410737797","doi":"https://doi.org/10.1109/access.2025.3573458"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3573458","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3573458","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3573458","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114110034","display_name":"S.M. Chu","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Shih-Chuan Chu","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103251327","display_name":"Chung\u2010Hsien Wu","orcid":"https://orcid.org/0000-0002-3947-2123"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chung-Hsien Wu","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5114110034"],"corresponding_institution_ids":["https://openalex.org/I91807558"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":2.8257,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.90154589,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"13","issue":null,"first_page":"92932","last_page":"92942"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9685999751091003,"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":0.8260502219200134},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5534930229187012},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5210484862327576},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4939020276069641},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4386335015296936},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.4135615825653076},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.41347184777259827},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36599981784820557},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18753880262374878},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.0836811363697052}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8260502219200134},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5534930229187012},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5210484862327576},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4939020276069641},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4386335015296936},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.4135615825653076},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.41347184777259827},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36599981784820557},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18753880262374878},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0836811363697052},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3573458","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3573458","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:ab55ee59e4c1472b9aaf150582c1b842","is_oa":true,"landing_page_url":"https://doaj.org/article/ab55ee59e4c1472b9aaf150582c1b842","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 92932-92942 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3573458","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3573458","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5411772072","display_name":null,"funder_award_id":"111-2221-E-006-150-MY3","funder_id":"https://openalex.org/F4320331164","funder_display_name":"National Science and Technology Council"}],"funders":[{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1635512741","https://openalex.org/W1974387177","https://openalex.org/W1995536493","https://openalex.org/W2094721231","https://openalex.org/W2593116425","https://openalex.org/W2892110446","https://openalex.org/W2952218014","https://openalex.org/W3031135612","https://openalex.org/W3096008106","https://openalex.org/W3096831136","https://openalex.org/W3161525290","https://openalex.org/W3197912330","https://openalex.org/W4221143458","https://openalex.org/W4221144097","https://openalex.org/W4225269836","https://openalex.org/W4226029295","https://openalex.org/W4232282348","https://openalex.org/W4281661987","https://openalex.org/W4319586149","https://openalex.org/W4372266968","https://openalex.org/W4372347086","https://openalex.org/W4375869120","https://openalex.org/W4380434618","https://openalex.org/W4385822340","https://openalex.org/W4392909903","https://openalex.org/W4402111962","https://openalex.org/W4402703066","https://openalex.org/W4403127014","https://openalex.org/W4404577192","https://openalex.org/W4408353691","https://openalex.org/W6762114000","https://openalex.org/W6779823529","https://openalex.org/W6850614898","https://openalex.org/W6857524394","https://openalex.org/W6863001916"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"In":[0,50],"recent":[1],"years,":[2],"speech":[3,80,126],"enhancement":[4],"research":[5],"has":[6,47],"increasingly":[7],"leveraged":[8],"deep":[9],"neural":[10],"network":[11],"models":[12,18],"to":[13,69,138],"improve":[14],"performance.":[15],"Although":[16,166],"these":[17],"often":[19],"achieve":[20],"strong":[21],"results":[22],"on":[23,199],"specific":[24],"datasets,":[25,174],"they":[26],"typically":[27],"require":[28],"substantial":[29,177],"memory":[30],"and":[31,142,148,163,196,202],"computational":[32],"resources,":[33],"limiting":[34],"their":[35],"practicality":[36],"in":[37,179],"real-world":[38],"applications.":[39],"Consequently,":[40],"evaluating":[41],"model":[42,65,85],"performance":[43,149],"across":[44],"diverse":[45],"datasets":[46],"become":[48],"essential.":[49],"this":[51],"work,":[52],"we":[53],"propose":[54],"a":[55,63,83,87],"novel":[56],"SE":[57,114,143],"framework,":[58],"termed":[59],"CDiffSE-AC,":[60],"which":[61,92],"integrates":[62],"diffusion":[64,84],"with":[66],"Actor\u2013Critic":[67],"techniques":[68],"address":[70],"the":[71,95,101,113,120,130,140,153,161,184,200],"limitations":[72],"of":[73,160,193],"existing":[74],"methods.":[75],"Our":[76],"approach":[77],"processes":[78],"noisy":[79,102],"inputs":[81,137],"using":[82,156],"alongside":[86],"pre-trained":[88],"large-scale":[89],"language":[90],"model,":[91],"serves":[93],"as":[94,109,136],"Actor":[96,141],"by":[97,123],"generating":[98],"labels":[99,105],"for":[100,112],"input.":[103],"These":[104],"are":[106,133],"subsequently":[107],"used":[108],"conditioning":[110],"information":[111],"model.":[115],"A":[116],"Critic":[117],"module":[118],"evaluates":[119],"enhanced":[121,131],"output":[122],"scoring":[124],"its":[125],"quality.":[127],"During":[128],"training,":[129],"outputs":[132],"recursively":[134],"reintroduced":[135],"both":[139],"models,":[144],"enabling":[145],"iterative":[146],"refinement":[147],"enhancement.":[150],"We":[151],"evaluate":[152],"proposed":[154],"method":[155],"two":[157],"different-sized":[158],"subsets":[159],"TIMIT":[162,201],"VCTK-DM":[164,203],"datasets.":[165],"CDiffSE-AC":[167,189],"yields":[168],"marginal":[169],"score":[170],"improvements":[171,192],"within":[172],"individual":[173],"it":[175],"demonstrates":[176],"gains":[178],"cross-dataset":[180],"evaluations,":[181],"significantly":[182],"outperforming":[183],"baseline":[185],"MOSE":[186],"method.":[187],"Specifically,":[188],"achieves":[190],"PESQ":[191],"0.15":[194],"(7.2%)":[195],"0.18":[197],"(7.5%)":[198],"test":[204],"sets,":[205],"respectively.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}