{"id":"https://openalex.org/W4416250485","doi":"https://doi.org/10.1109/waspaa66052.2025.11231015","title":"EffDiffSE: Efficient Diffusion-Based Frequency-Domain Speech Enhancement with Hybrid Discriminative and Generative DNNs","display_name":"EffDiffSE: Efficient Diffusion-Based Frequency-Domain Speech Enhancement with Hybrid Discriminative and Generative DNNs","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416250485","doi":"https://doi.org/10.1109/waspaa66052.2025.11231015"},"language":null,"primary_location":{"id":"doi:10.1109/waspaa66052.2025.11231015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11231015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5010250251","display_name":"Yihui Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yihui Fu","raw_affiliation_strings":["TU Braunschweig,Institute for Communications Technology,Braunschweig,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Braunschweig,Institute for Communications Technology,Braunschweig,Germany","institution_ids":["https://openalex.org/I94509681"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111335033","display_name":"Renzheng Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Renzheng Shi","raw_affiliation_strings":["TU Braunschweig,Institute for Communications Technology,Braunschweig,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Braunschweig,Institute for Communications Technology,Braunschweig,Germany","institution_ids":["https://openalex.org/I94509681"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110895535","display_name":"Marvin Sach","orcid":null},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marvin Sach","raw_affiliation_strings":["TU Braunschweig,Institute for Communications Technology,Braunschweig,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Braunschweig,Institute for Communications Technology,Braunschweig,Germany","institution_ids":["https://openalex.org/I94509681"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018190338","display_name":"Wouter Tirry","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wouter Tirry","raw_affiliation_strings":["Goodix Technology (Belgium) BV,Leuven,Belgium,3000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Goodix Technology (Belgium) BV,Leuven,Belgium,3000","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002593702","display_name":"Tim Fingscheidt","orcid":"https://orcid.org/0000-0002-8895-5041"},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tim Fingscheidt","raw_affiliation_strings":["TU Braunschweig,Institute for Communications Technology,Braunschweig,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Braunschweig,Institute for Communications Technology,Braunschweig,Germany","institution_ids":["https://openalex.org/I94509681"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41869961,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9894000291824341,"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":0.9894000291824341,"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":0.003700000001117587,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0013000000035390258,"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/discriminative-model","display_name":"Discriminative model","score":0.8188999891281128},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7542999982833862},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6974999904632568},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.5491999983787537},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.43299999833106995},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4189999997615814},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.39149999618530273},{"id":"https://openalex.org/keywords/psychoacoustics","display_name":"Psychoacoustics","score":0.37700000405311584}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8188999891281128},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7542999982833862},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7063000202178955},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6974999904632568},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5572999715805054},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.5491999983787537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49709999561309814},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.43299999833106995},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4189999997615814},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.39149999618530273},{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.37700000405311584},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30970001220703125},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.27000001072883606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11231015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11231015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2127851351","https://openalex.org/W2516001803","https://openalex.org/W2760103357","https://openalex.org/W2952218014","https://openalex.org/W3025844872","https://openalex.org/W3191448984","https://openalex.org/W3196475561","https://openalex.org/W4221144097","https://openalex.org/W4225302959","https://openalex.org/W4297841790","https://openalex.org/W4380434618","https://openalex.org/W4384080510","https://openalex.org/W4385822888","https://openalex.org/W4385823353","https://openalex.org/W4387195417","https://openalex.org/W4392903345","https://openalex.org/W4402112079","https://openalex.org/W4402112289","https://openalex.org/W4402112296","https://openalex.org/W4402112483","https://openalex.org/W4402112506","https://openalex.org/W4408354850"],"related_works":[],"abstract_inverted_index":{"Diffusion":[0],"approaches":[1],"to":[2,9,26,104,110,135],"speech":[3,12,43],"enhancement":[4,44],"gain":[5],"immense":[6],"attention":[7],"due":[8,25],"their":[10],"improved":[11],"component":[13],"reconstruction":[14],"capability.":[15],"However,":[16],"they":[17],"usually":[18],"suffer":[19],"from":[20],"high":[21],"inference":[22,93,157],"computational":[23,158],"complexity":[24,159],"multiple":[27],"iterations":[28],"during":[29,90],"the":[30,63,69,105,112,120,128,136],"reverse":[31,87,107],"process.":[32],"In":[33],"this":[34],"paper,":[35],"we":[36,61,82],"propose":[37],"EffDiffSE,":[38],"an":[39,99,132],"efficient":[40,86],"diffusion-based":[41],"frequency-domain":[42,141],"model":[45,67],"with":[46,72,94],"a":[47,73,84],"hybrid":[48],"discriminative":[49],"condition":[50],"DNN":[51],"and":[52,77,92,117,140,156],"generative":[53],"score":[54,78],"DNN.":[55],"Our":[56],"contributions":[57],"are":[58],"three-fold.":[59],"First,":[60],"formulate":[62],"powerful":[64],"time-domain":[65],"Universe++":[66],"in":[68],"frequency":[70],"domain":[71],"combined":[74],"psychoacoustic":[75],"loss":[76,101],"matching":[79],"loss.":[80],"Second,":[81],"achieve":[83],"single-step":[85,106],"process":[88,108],"both":[89],"training":[91],"noise-consistent":[95],"Langevin":[96],"dynamics.":[97],"Third,":[98],"auxiliary":[100],"is":[102],"applied":[103],"output":[109],"improve":[111],"diffusion":[113,142],"performance":[114],"further.":[115],"Trained":[116],"evaluated":[118],"on":[119],"URGENT":[121],"2024":[122],"Speech":[123],"Enhancement":[124],"Challenge":[125],"data":[126],"splits,":[127],"proposed":[129],"EffDiffSE":[130],"achieves":[131],"MOS":[133],"comparable":[134],"top":[137],"reported":[138],"time-":[139],"baseline":[143],"methods,":[144],"while":[145],"excelling":[146],"them":[147],"by":[148],">0.2":[149],"PESQ":[150],"points,":[151],"showing":[152],"significantly":[153],"less":[154],"hallucination":[155],"(3.9":[160],"GMAC/s":[161],"vs.":[162],"58":[163],"...":[164],"7600":[165],"GMAC/s).":[166]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-14T00:00:00"}