{"id":"https://openalex.org/W4415708097","doi":"https://doi.org/10.1109/icme59968.2025.11210008","title":"Dancing with Noise: Advancing Generative Speech Enhancement with Distribution Augmentation","display_name":"Dancing with Noise: Advancing Generative Speech Enhancement with Distribution Augmentation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708097","doi":"https://doi.org/10.1109/icme59968.2025.11210008"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5100719640","display_name":"Lei Yue","orcid":"https://orcid.org/0000-0003-0327-2776"},"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":true,"raw_author_name":"Yue Lei","raw_affiliation_strings":["University of Electronic Science and Technology of China,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020806354","display_name":"Siqi Yang","orcid":"https://orcid.org/0000-0002-4990-0195"},"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":"Siqi Yang","raw_affiliation_strings":["University of Electronic Science and Technology of China,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,Chengdu,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"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043425721","display_name":"Xueting Liu","orcid":"https://orcid.org/0000-0002-5681-8464"},"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":"Xueting Liu","raw_affiliation_strings":["University of Electronic Science and Technology of China,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034789908","display_name":"Ting Zhong","orcid":"https://orcid.org/0000-0002-8163-3146"},"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":"Ting Zhong","raw_affiliation_strings":["University of Electronic Science and Technology of China,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,Chengdu,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"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100719640"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":1.4129,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86215397,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9697999954223633,"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":0.9697999954223633,"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/T11448","display_name":"Face recognition and analysis","score":0.007199999876320362,"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"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.005499999970197678,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.7175999879837036},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5684000253677368},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.5519999861717224},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.44190001487731934},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4325999915599823},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.3928999900817871},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36149999499320984}],"concepts":[{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.7175999879837036},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6055999994277954},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5684000253677368},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.5519999861717224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44339999556541443},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.44190001487731934},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4325999915599823},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42329999804496765},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3928999900817871},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37450000643730164},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36149999499320984},{"id":"https://openalex.org/C177454536","wikidata":"https://www.wikidata.org/wiki/Q578290","display_name":"Emphasis (telecommunications)","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3434000015258789},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25920000672340393},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2524999976158142},{"id":"https://openalex.org/C102094743","wikidata":"https://www.wikidata.org/wiki/Q133871","display_name":"Normal distribution","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11210008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1991111872","https://openalex.org/W2144404214","https://openalex.org/W2233657726","https://openalex.org/W2516001803","https://openalex.org/W2766672686","https://openalex.org/W2991015288","https://openalex.org/W3096408984","https://openalex.org/W3162493033","https://openalex.org/W4221144097","https://openalex.org/W4367281387","https://openalex.org/W4380434618","https://openalex.org/W4384080510","https://openalex.org/W4385823353","https://openalex.org/W4388620484","https://openalex.org/W4399345616","https://openalex.org/W4403095773"],"related_works":[],"abstract_inverted_index":{"Instead":[0],"of":[1,27,52,67],"using":[2],"a":[3,14,40,49,57],"standard":[4],"diffusion":[5,20],"model,":[6],"most":[7],"diffusion-based":[8],"speech":[9],"enhancement":[10],"methods":[11,104],"additionally":[12],"incorporate":[13],"mean":[15,37,61],"interpolation":[16,38],"strategy":[17,29],"into":[18],"the":[19,23,90],"process.":[21],"However,":[22],"role":[24],"and":[25,55,108],"impact":[26],"this":[28,33,72],"remain":[30],"unclear.":[31],"In":[32],"study,":[34],"we":[35,74],"investigate":[36],"from":[39],"data":[41],"augmentation":[42,54,85],"perspective,":[43],"demonstrating":[44],"that":[45,87,99],"it":[46],"serves":[47],"as":[48],"specific":[50],"form":[51],"distribution":[53,84,92],"provides":[56],"unified":[58],"formula":[59],"for":[60],"interpolation,":[62],"which":[63],"encompasses":[64],"current":[65],"variations":[66],"such":[68],"strategy.":[69],"Building":[70],"on":[71],"insight,":[73],"propose":[75],"DANS":[76,100],"(Distribution":[77],"Augmentation":[78],"with":[79],"Noise":[80],"Shuffling),":[81],"an":[82],"advanced":[83],"method":[86],"further":[88],"expands":[89],"training":[91],"through":[93],"noise-shuffling":[94],"techniques.":[95],"Experimental":[96],"results":[97],"show":[98],"consistently":[101],"outperforms":[102],"existing":[103],"in":[105],"matched,":[106],"cross-dataset,":[107],"low-data":[109],"scenarios.":[110],"Codes":[111],"are":[112],"publicly":[113],"available":[114],"at":[115],"https://github.com/ICDM-UESTC/DANCE.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-30T00:00:00"}