{"id":"https://openalex.org/W4408352278","doi":"https://doi.org/10.1109/icassp49660.2025.10890477","title":"Conditional Latent Diffusion-Based Speech Enhancement via Dual Context Learning","display_name":"Conditional Latent Diffusion-Based Speech Enhancement via Dual Context Learning","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352278","doi":"https://doi.org/10.1109/icassp49660.2025.10890477"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5103758307","display_name":"Shengkui Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengkui Zhao","raw_affiliation_strings":["Alibaba Group,Tongyi Lab,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Tongyi Lab,Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060530570","display_name":"Zexu Pan","orcid":"https://orcid.org/0000-0002-8106-1176"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zexu Pan","raw_affiliation_strings":["Alibaba Group,Tongyi Lab,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Tongyi Lab,Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101654458","display_name":"Kun Zhou","orcid":"https://orcid.org/0000-0002-7869-4474"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Zhou","raw_affiliation_strings":["Alibaba Group,Tongyi Lab,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Tongyi Lab,Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101568886","display_name":"Yukun Ma","orcid":"https://orcid.org/0000-0002-4419-4287"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yukun Ma","raw_affiliation_strings":["Alibaba Group,Tongyi Lab,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Tongyi Lab,Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100393921","display_name":"Chong Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chong Zhang","raw_affiliation_strings":["Alibaba Group,Tongyi Lab,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Tongyi Lab,Singapore","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100595427","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0002-3724-4581"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":["Alibaba Group,Tongyi Lab,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Tongyi Lab,Singapore","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"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":0.9976000189781189,"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":0.9976000189781189,"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":0.9926999807357788,"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/T11309","display_name":"Music and Audio Processing","score":0.9264000058174133,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7512508034706116},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.638770341873169},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5536367893218994},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5364366769790649},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4798383414745331},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.45648500323295593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42952844500541687},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.09576666355133057},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06357342004776001}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7512508034706116},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.638770341873169},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5536367893218994},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5364366769790649},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4798383414745331},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.45648500323295593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42952844500541687},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.09576666355133057},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06357342004776001},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W2516001803","https://openalex.org/W2593116425","https://openalex.org/W2603567530","https://openalex.org/W2952218014","https://openalex.org/W2964058413","https://openalex.org/W3097906045","https://openalex.org/W3197912330","https://openalex.org/W4221144097","https://openalex.org/W4225302959","https://openalex.org/W4312933868","https://openalex.org/W4372341094","https://openalex.org/W4380434618","https://openalex.org/W4384080510","https://openalex.org/W4388821018","https://openalex.org/W4402111962","https://openalex.org/W6640963894","https://openalex.org/W6679045638","https://openalex.org/W6757817989","https://openalex.org/W6769627184","https://openalex.org/W6779823529","https://openalex.org/W6788990321","https://openalex.org/W6838843145","https://openalex.org/W6848208918","https://openalex.org/W6849109464","https://openalex.org/W6851290578"],"related_works":["https://openalex.org/W1630865680","https://openalex.org/W4214692512","https://openalex.org/W2317351040","https://openalex.org/W2373767407","https://openalex.org/W2952466936","https://openalex.org/W2516933085","https://openalex.org/W1988622314","https://openalex.org/W3168109306","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"Recently,":[0],"the":[1,21,56,107,121,148,152,155,159,163,176,180,195],"application":[2],"of":[3,51,59,110,154,179,199],"diffusion":[4,60,79],"probabilistic":[5],"models":[6,61,201],"has":[7],"advanced":[8],"speech":[9,46,63,113],"enhancement":[10],"through":[11],"generative":[12],"approaches.":[13],"However,":[14],"existing":[15,185],"diffusion-based":[16,186],"methods":[17,41],"have":[18,42],"focused":[19],"on":[20,135],"generation":[22,33,156],"process":[23,161],"in":[24,144],"high-dimensional":[25],"waveform":[26],"or":[27],"spectral":[28],"domains,":[29],"leading":[30],"to":[31,93,105,130,166,184,202],"increased":[32],"complexity":[34,153],"and":[35,114,124,139,169,193],"slower":[36],"inference":[37],"speeds.":[38],"Additionally,":[39],"these":[40,67],"primarily":[43],"modelled":[44],"clean":[45,112],"distributions,":[47,53],"with":[48,82,189],"limited":[49],"exploration":[50],"noise":[52,116,119,171,204],"thereby":[54],"constraining":[55],"discriminative":[57],"capability":[58,198],"for":[62],"enhancement.":[64],"To":[65],"address":[66],"issues,":[68],"we":[69],"propose":[70],"a":[71,76,89,97,125,145],"novel":[72],"approach":[73,182],"that":[74],"integrates":[75],"conditional":[77],"latent":[78,99,108,137,149],"model":[80,127],"(cLDM)":[81],"dual-context":[83],"learning":[84],"(DCL).":[85],"Our":[86,173],"method":[87],"utilizes":[88],"variational":[90],"autoencoder":[91],"(VAE)":[92],"compress":[94],"mel-spectrograms":[95],"into":[96,117],"low-dimensional":[98],"space.":[100],"We":[101],"then":[102],"apply":[103],"cLDM":[104],"transform":[106],"representations":[109,138,150],"both":[111],"background":[115],"Gaussian":[118],"by":[120],"DCL":[122,160],"process,":[123,133,157],"parameterized":[126],"is":[128],"trained":[129],"reverse":[131],"this":[132],"conditioned":[134],"noisy":[136],"text":[140],"embeddings.":[141],"By":[142],"operating":[143],"lower-dimensional":[146],"space,":[147],"reduce":[151],"while":[158],"enhances":[162],"model\u2019s":[164],"ability":[165],"handle":[167],"diverse":[168],"unseen":[170],"environments.":[172],"experiments":[174],"demonstrate":[175],"strong":[177],"performance":[178],"proposed":[181],"compared":[183],"methods,":[187],"even":[188],"fewer":[190],"iterative":[191],"steps,":[192],"highlight":[194],"superior":[196],"generalization":[197],"our":[200],"out-of-domain":[203],"datasets.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}