{"id":"https://openalex.org/W4409426258","doi":"https://doi.org/10.1109/lsp.2025.3560622","title":"Progressive Skip Connection Improves Consistency of Diffusion-Based Speech Enhancement","display_name":"Progressive Skip Connection Improves Consistency of Diffusion-Based Speech Enhancement","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409426258","doi":"https://doi.org/10.1109/lsp.2025.3560622"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2025.3560622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3560622","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","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/A5110542243","display_name":"Yue Lei","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Lei","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China","University of Electronic Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0009-0009-9892-7018","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046991896","display_name":"Xucheng Luo","orcid":"https://orcid.org/0000-0002-3407-9242"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xucheng Luo","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China","University of Electronic Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0002-3407-9242","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090741164","display_name":"Wenxin Tai","orcid":"https://orcid.org/0000-0001-7364-8324"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxin Tai","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China","University of Electronic Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0001-7364-8324","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100403505","display_name":"Fan Zhou","orcid":"https://orcid.org/0000-0002-8038-8150"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Zhou","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China","University of Electronic Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0002-8038-8150","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":1.8049,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.83514346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"32","issue":null,"first_page":"1650","last_page":"1654"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9951000213623047,"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":0.9951000213623047,"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/T13289","display_name":"Infant Health and Development","score":0.9185000061988831,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6447794437408447},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6199771761894226},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5896711349487305},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5833514928817749},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5764695405960083},{"id":"https://openalex.org/keywords/connection","display_name":"Connection (principal bundle)","score":0.5074490904808044},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3600672781467438},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29364973306655884},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24359571933746338},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1381162703037262},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08503353595733643}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6447794437408447},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6199771761894226},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5896711349487305},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5833514928817749},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5764695405960083},{"id":"https://openalex.org/C13355873","wikidata":"https://www.wikidata.org/wiki/Q2920850","display_name":"Connection (principal bundle)","level":2,"score":0.5074490904808044},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3600672781467438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29364973306655884},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24359571933746338},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1381162703037262},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08503353595733643},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3560622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3560622","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3976612152","display_name":null,"funder_award_id":"62176043","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5983462902","display_name":"\u56fe\u5b66\u4e60\u4e2d\u7684\u53ef\u89e3\u91ca\u6027\u7814\u7a76","funder_award_id":"62072077","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1968939597","https://openalex.org/W2044893557","https://openalex.org/W2067295501","https://openalex.org/W2124537004","https://openalex.org/W2128653836","https://openalex.org/W2144404214","https://openalex.org/W2233657726","https://openalex.org/W2559260703","https://openalex.org/W2603567530","https://openalex.org/W2694896445","https://openalex.org/W2950306824","https://openalex.org/W2952218014","https://openalex.org/W2963341071","https://openalex.org/W3096408984","https://openalex.org/W3160085755","https://openalex.org/W3160324929","https://openalex.org/W3201306501","https://openalex.org/W4221144097","https://openalex.org/W4297841790","https://openalex.org/W4367281387","https://openalex.org/W4372347392","https://openalex.org/W4375869120","https://openalex.org/W4380434618","https://openalex.org/W4382202691","https://openalex.org/W4384080510","https://openalex.org/W4385822788","https://openalex.org/W4385823353","https://openalex.org/W4388620484","https://openalex.org/W4392910516","https://openalex.org/W4402112296","https://openalex.org/W6752051073","https://openalex.org/W6753417141","https://openalex.org/W6762114000","https://openalex.org/W6779823529","https://openalex.org/W6783182287","https://openalex.org/W6786375611","https://openalex.org/W6798721538","https://openalex.org/W6851069163","https://openalex.org/W6855261814"],"related_works":["https://openalex.org/W587735977","https://openalex.org/W1978142926","https://openalex.org/W3157395178","https://openalex.org/W184455116","https://openalex.org/W2058473748","https://openalex.org/W963756281","https://openalex.org/W2371558776","https://openalex.org/W2045569473","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,24,47,121,147],"generative":[3],"modeling":[4],"have":[5],"successfully":[6],"integrated":[7],"denoising":[8],"diffusion":[9],"probabilistic":[10],"models":[11,57],"(DDPMs)":[12],"into":[13],"the":[14,30,34,80,83,87,98,119,125,129,142],"domain":[15],"of":[16,29,144],"speech":[17,109],"enhancement":[18],"(SE).":[19],"Despite":[20],"their":[21],"considerable":[22],"advantages":[23],"generalizability,":[25],"ensuring":[26],"semantic":[27],"consistency":[28,60],"generated":[31],"samples":[32],"with":[33,61],"condition":[35,62,88,130],"signal":[36,89,131],"remains":[37],"a":[38,112],"formidable":[39],"challenge.":[40],"Inspired":[41],"by":[42],"techniques":[43],"addressing":[44],"posterior":[45],"collapse":[46],"variational":[48],"autoencoders,":[49],"we":[50,96],"explore":[51],"skip":[52,70,114],"connections":[53,71],"within":[54],"diffusion-based":[55],"SE":[56],"to":[58,106,117],"improve":[59],"signals.":[63],"However,":[64],"experiments":[65],"reveal":[66],"that":[67,79],"simply":[68],"adding":[69],"is":[72,155],"ineffective":[73],"and":[74,86,110,128,150],"even":[75],"counterproductive.":[76],"We":[77],"argue":[78],"independence":[81],"between":[82,124],"predictive":[84],"target":[85],"causes":[90],"this":[91],"failure.":[92],"To":[93],"address":[94],"this,":[95],"modify":[97],"training":[99],"objective":[100],"from":[101],"predicting":[102,107],"random":[103],"Gaussian":[104],"noise":[105],"clean":[108],"propose":[111],"progressive":[113],"connection":[115],"strategy":[116],"mitigate":[118],"decrease":[120],"mutual":[122],"information":[123],"layer's":[126],"output":[127],"as":[132],"network":[133],"depth":[134],"increases.":[135],"Experiments":[136],"on":[137],"two":[138],"standard":[139],"datasets":[140],"demonstrate":[141],"effectiveness":[143],"our":[145],"approach":[146],"both":[148],"seen":[149],"unseen":[151],"scenarios.":[152],"The":[153],"code":[154],"publicly":[156],"available":[157],"at":[158],"https://github.com/ICDM-UESTC/SCSE.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}