{"id":"https://openalex.org/W4399345616","doi":"https://doi.org/10.1109/taslp.2024.3407533","title":"A Variance-Preserving Interpolation Approach for Diffusion Models With Applications to Single Channel Speech Enhancement and Recognition","display_name":"A Variance-Preserving Interpolation Approach for Diffusion Models With Applications to Single Channel Speech Enhancement and Recognition","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4399345616","doi":"https://doi.org/10.1109/taslp.2024.3407533"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3407533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3407533","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","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/A5089001438","display_name":"Zilu Guo","orcid":"https://orcid.org/0009-0000-0486-6088"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zilu Guo","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0000-0486-6088","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100434900","display_name":"Qing Wang","orcid":"https://orcid.org/0000-0003-3843-3920"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Wang","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-3843-3920","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-2387-0389","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076812698","display_name":"Jia Pan","orcid":"https://orcid.org/0000-0001-9003-2054"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia Pan","raw_affiliation_strings":["iFLYTEK Research, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039181878","display_name":"Qingfeng Liu","orcid":"https://orcid.org/0000-0001-5437-4946"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing-Feng Liu","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1892-2551","affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0229,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.9228009,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"3025","last_page":"3038"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9970999956130981,"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":0.9959999918937683,"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/robustness","display_name":"Robustness (evolution)","score":0.7042369842529297},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6886297464370728},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.6659680604934692},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6518638134002686},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.620837390422821},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4875628352165222},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.45855042338371277},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4387945830821991},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.43783053755760193},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42944082617759705},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4256143271923065},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4103260934352875},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37407076358795166},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36197420954704285},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.237978994846344},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.18134725093841553}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7042369842529297},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6886297464370728},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6659680604934692},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6518638134002686},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.620837390422821},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4875628352165222},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45855042338371277},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4387945830821991},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.43783053755760193},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42944082617759705},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4256143271923065},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4103260934352875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37407076358795166},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36197420954704285},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.237978994846344},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.18134725093841553},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3407533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3407533","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G1713836045","display_name":null,"funder_award_id":"62171427","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":63,"referenced_works":["https://openalex.org/W1873645982","https://openalex.org/W1968939597","https://openalex.org/W2013035813","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2110322414","https://openalex.org/W2113131123","https://openalex.org/W2128653836","https://openalex.org/W2144404214","https://openalex.org/W2291877678","https://openalex.org/W2516001803","https://openalex.org/W2516547830","https://openalex.org/W2559260703","https://openalex.org/W2603567530","https://openalex.org/W2605589342","https://openalex.org/W2755891984","https://openalex.org/W2940275453","https://openalex.org/W2952218014","https://openalex.org/W2962892438","https://openalex.org/W2981022124","https://openalex.org/W2998832642","https://openalex.org/W3028077980","https://openalex.org/W3092864146","https://openalex.org/W3097906045","https://openalex.org/W3099330747","https://openalex.org/W3102190437","https://openalex.org/W3157804362","https://openalex.org/W3160085755","https://openalex.org/W3160324929","https://openalex.org/W3163162786","https://openalex.org/W3174264304","https://openalex.org/W3191850102","https://openalex.org/W3196863408","https://openalex.org/W3197032408","https://openalex.org/W3197912330","https://openalex.org/W3206558844","https://openalex.org/W4211127940","https://openalex.org/W4221143458","https://openalex.org/W4221144097","https://openalex.org/W4225269836","https://openalex.org/W4225303417","https://openalex.org/W4297841603","https://openalex.org/W4297841790","https://openalex.org/W4312933868","https://openalex.org/W4372260037","https://openalex.org/W4372266968","https://openalex.org/W4372341905","https://openalex.org/W4372347392","https://openalex.org/W4375869120","https://openalex.org/W4380434618","https://openalex.org/W4384080510","https://openalex.org/W4385807442","https://openalex.org/W4385822788","https://openalex.org/W6734797129","https://openalex.org/W6762114000","https://openalex.org/W6765775151","https://openalex.org/W6779823529","https://openalex.org/W6783182287","https://openalex.org/W6786375611","https://openalex.org/W6797906067","https://openalex.org/W6798721538","https://openalex.org/W6802527329","https://openalex.org/W6803559545"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2110523656","https://openalex.org/W1482209366","https://openalex.org/W2521627374"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,128],"propose":[4],"a":[5,41,85,107],"variance-preserving":[6,25],"interpolation":[7,26,50],"framework":[8],"to":[9,79,154],"improve":[10],"diffusion":[11,27,51],"models":[12],"for":[13,40],"single-channel":[14],"speech":[15,20],"enhancement":[16],"(SE)":[17],"and":[18,36,59,71,94,102,163,180],"automatic":[19],"recognition":[21],"(ASR).":[22],"This":[23],"new":[24],"model":[28,52,135],"(VPIDM)":[29],"approach":[30],"requires":[31],"only":[32],"25":[33],"iterative":[34],"steps":[35],"obviates":[37],"the":[38,47,62,66,72,76,80,89,130,133,158,172],"need":[39],"corrector,":[42],"an":[43],"essential":[44],"element":[45],"in":[46,100,148,166],"existing":[48],"variance-exploding":[49],"(VEIDM).":[53],"Two":[54],"notable":[55],"distinctions":[56],"between":[57],"VPIDM":[58,105,162],"VEIDM":[60,164],"are":[61,183],"scaling":[63],"function":[64],"of":[65,68,88,132,160,175],"mean":[67],"state":[69],"variables":[70],"constraint":[73],"imposed":[74],"on":[75,113],"variance":[77],"relative":[78],"mean's":[81],"scale.":[82],"We":[83],"conduct":[84],"systematic":[86],"exploration":[87],"theoretical":[90],"mechanism":[91],"underlying":[92],"VPIDM,":[93],"develop":[95],"insights":[96],"regarding":[97],"VPIDM's":[98,119,145],"applications":[99],"SE":[101,125],"ASR":[103,168],"using":[104],"as":[106],"frontend.":[108],"Our":[109],"proposed":[110,134,177],"approach,":[111],"evaluated":[112],"two":[114],"distinct":[115],"data":[116],"sets,":[117],"demonstrates":[118],"superior":[120],"performances":[121],"over":[122],"conventional":[123],"discriminative":[124],"algorithms.":[126],"Furthermore,":[127,156],"assess":[129],"performance":[131],"under":[136],"varying":[137],"signal-to-noise":[138],"ratio":[139],"(SNR)":[140],"levels.":[141],"The":[142],"investigation":[143],"reveals":[144],"improved":[146],"robustness":[147],"target":[149],"noise":[150],"elimination":[151],"when":[152],"compared":[153],"VEIDM.":[155],"utilizing":[157],"mid-outputs":[159],"both":[161],"results":[165],"enhanced":[167],"accuracies,":[169],"thereby":[170],"highlighting":[171],"practical":[173],"efficacy":[174],"our":[176],"approach.":[178],"Code":[179],"audio":[181],"examples":[182],"available":[184],"online":[185],"<uri":[186],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[187],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/zelokuo/VPIDM</uri>":[188],".":[189]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}