{"id":"https://openalex.org/W4415433797","doi":"https://doi.org/10.21437/interspeech.2025-350","title":"MDDM: A Multi-view Discriminative Enhanced Diffusion-based Model for Speech Enhancement","display_name":"MDDM: A Multi-view Discriminative Enhanced Diffusion-based Model for Speech Enhancement","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433797","doi":"https://doi.org/10.21437/interspeech.2025-350"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-350","doi":"https://doi.org/10.21437/interspeech.2025-350","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-350","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.13029","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Nan Xu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nan Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079906589","display_name":"Zhaolong Huang","orcid":"https://orcid.org/0009-0003-9741-7864","observed_orcids":["https://orcid.org/0009-0003-9741-7864"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaolong Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Xiaonan Zhi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaonan Zhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4078","last_page":"4082"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.9990000128746033,"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":0.00039999998989515007,"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"}},{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/speech-enhancement","display_name":"speech enhancement","score":0.9980000257492065},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.8009999990463257},{"id":"https://openalex.org/keywords/spectrogram-generation","display_name":"spectrogram generation","score":0.8259999752044678},{"id":"https://openalex.org/keywords/noise-robust-speech-enhancement","display_name":"noise-robust speech enhancement","score":0.4729999899864197},{"id":"https://openalex.org/keywords/time-frequency-features","display_name":"time-frequency features","score":0.5260000228881836}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5982000231742859},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5509999990463257},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5497000217437744},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5264999866485596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5006999969482422},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3725999891757965},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.29010000824928284},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2025-350","doi":"https://doi.org/10.21437/interspeech.2025-350","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-350","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.13029","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.13029","pdf_url":"https://arxiv.org/pdf/2505.13029","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.13029","doi":"https://doi.org/10.48550/arxiv.2505.13029","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.13029","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.13029","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.13029","pdf_url":"https://arxiv.org/pdf/2505.13029","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415433797.pdf","grobid_xml":"https://content.openalex.org/works/W4415433797.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4403095773","https://openalex.org/W4375869120","https://openalex.org/W4402112093","https://openalex.org/W4380434618","https://openalex.org/W4416250485","https://openalex.org/W4386907506","https://openalex.org/W4408352278","https://openalex.org/W4382202691","https://openalex.org/W4411724981","https://openalex.org/W4412403567"],"abstract_inverted_index":{"With":[0],"the":[1,22,54,71,75,91,94,102,108,127],"development":[2],"of":[3,14,56,65,93,129],"deep":[4],"learning,":[5],"speech":[6,15,33,83],"enhancement":[7],"has":[8],"been":[9],"greatly":[10],"optimized":[11],"in":[12],"terms":[13],"quality.":[16],"Previous":[17],"methods":[18],"typically":[19],"focus":[20],"on":[21,118,132],"discriminative":[23,67,76,97],"supervised":[24],"learning":[25],"or":[26,35,134],"generative":[27],"modeling,":[28],"which":[29],"tends":[30],"to":[31,81,90,112],"introduce":[32],"distortions":[34],"high":[36],"computational":[37],"cost.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42,52],"propose":[43],"MDDM,":[44,130],"a":[45,66,119,123],"Multi-view":[46],"Discriminative":[47],"enhanced":[48],"Diffusion-based":[49],"Model.":[50],"Specifically,":[51],"take":[53],"features":[55],"three":[57],"domains":[58],"(time,":[59],"frequency":[60],"and":[61,99,122],"noise)":[62],"as":[63],"inputs":[64],"prediction":[68],"network,":[69],"generating":[70],"preliminary":[72],"spectrogram.":[73],"Then,":[74],"output":[77,98],"can":[78,106],"be":[79],"converted":[80],"clean":[82,100],"by":[84],"several":[85],"inference":[86],"sampling":[87,104],"steps.":[88],"Due":[89],"intersection":[92],"distributions":[95],"between":[96],"target,":[101],"smaller":[103],"steps":[105],"achieve":[107],"competitive":[109],"performance":[110],"compared":[111],"other":[113],"diffusion-based":[114],"methods.":[115],"Experiments":[116],"conducted":[117],"public":[120],"dataset":[121,125],"realworld":[124],"validate":[126],"effectiveness":[128],"either":[131],"subjective":[133],"objective":[135],"metric.":[136]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-10-24T00:00:00"}