{"id":"https://openalex.org/W7148345280","doi":"https://doi.org/10.1109/asru65441.2025.11434658","title":"Lightweight Wasserstein Audio-Visual Model for Unified Speech Enhancement and Separation","display_name":"Lightweight Wasserstein Audio-Visual Model for Unified Speech Enhancement and Separation","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148345280","doi":"https://doi.org/10.1109/asru65441.2025.11434658"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434658","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5125775831","display_name":"Jisoo Park","orcid":null},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jisoo Park","raw_affiliation_strings":["Chung-Ang University,Department of Artificial Intelligence,South Korea"],"affiliations":[{"raw_affiliation_string":"Chung-Ang University,Department of Artificial Intelligence,South Korea","institution_ids":["https://openalex.org/I67900169"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025005134","display_name":"Seonghak Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seonghak Lee","raw_affiliation_strings":["Chung-Ang University,Department of Computer Science and Engineering,South Korea"],"affiliations":[{"raw_affiliation_string":"Chung-Ang University,Department of Computer Science and Engineering,South Korea","institution_ids":["https://openalex.org/I67900169"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059457064","display_name":"Guisik Kim","orcid":"https://orcid.org/0000-0002-8254-0881"},"institutions":[{"id":"https://openalex.org/I4210131650","display_name":"Korea Electronics Technology Institute","ror":"https://ror.org/039k6f508","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210089395","https://openalex.org/I4210131650"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Guisik Kim","raw_affiliation_strings":["Korea Electronics Technology Institute,South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Electronics Technology Institute,South Korea","institution_ids":["https://openalex.org/I4210131650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069545619","display_name":"Taewoo Kim","orcid":"https://orcid.org/0009-0008-6092-6637"},"institutions":[{"id":"https://openalex.org/I4210131650","display_name":"Korea Electronics Technology Institute","ror":"https://ror.org/039k6f508","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210089395","https://openalex.org/I4210131650"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Taewoo Kim","raw_affiliation_strings":["Korea Electronics Technology Institute,South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Electronics Technology Institute,South Korea","institution_ids":["https://openalex.org/I4210131650"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045083125","display_name":"Junseok Kwon","orcid":"https://orcid.org/0000-0001-9526-7549"},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Junseok Kwon","raw_affiliation_strings":["Chung-Ang University,Department of Artificial Intelligence,South Korea"],"affiliations":[{"raw_affiliation_string":"Chung-Ang University,Department of Artificial Intelligence,South Korea","institution_ids":["https://openalex.org/I67900169"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5125775831"],"corresponding_institution_ids":["https://openalex.org/I67900169"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.75210775,"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":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9650999903678894,"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":0.9650999903678894,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.008500000461935997,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.006399999838322401,"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":0.6432999968528748},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4828999936580658},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.35350000858306885},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.3434000015258789},{"id":"https://openalex.org/keywords/separation-method","display_name":"Separation method","score":0.3181999921798706},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.31529998779296875},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.3095000088214874}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6432999968528748},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5188999772071838},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4828999936580658},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.35350000858306885},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.329800009727478},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3188000023365021},{"id":"https://openalex.org/C3018256011","wikidata":"https://www.wikidata.org/wiki/Q898987","display_name":"Separation method","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3176000118255615},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.3095000088214874},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30730000138282776},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.27230000495910645},{"id":"https://openalex.org/C51432778","wikidata":"https://www.wikidata.org/wiki/Q1259145","display_name":"Independent component analysis","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.25589999556541443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434658","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.48623600602149963}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W2015143272","https://openalex.org/W2044893557","https://openalex.org/W2072634211","https://openalex.org/W2096733369","https://openalex.org/W2221409856","https://openalex.org/W2325939864","https://openalex.org/W2883322837","https://openalex.org/W2890952074","https://openalex.org/W2962866211","https://openalex.org/W2963082324","https://openalex.org/W2964171275","https://openalex.org/W2965390715","https://openalex.org/W2972513594","https://openalex.org/W2973010927","https://openalex.org/W3004146833","https://openalex.org/W3005621653","https://openalex.org/W3008400075","https://openalex.org/W3116298410","https://openalex.org/W3131332223","https://openalex.org/W3161480375","https://openalex.org/W4221143458","https://openalex.org/W4232282348","https://openalex.org/W4289665794","https://openalex.org/W4385807442","https://openalex.org/W4385823088","https://openalex.org/W4391021717","https://openalex.org/W4392903251","https://openalex.org/W4402535317"],"related_works":[],"abstract_inverted_index":{"Speech":[0,4],"Enhancement":[1],"(SE)":[2],"and":[3,25,43,55,62,72,79,89,97,123],"Separation":[5],"(SS)":[6],"have":[7,38],"traditionally":[8],"been":[9],"treated":[10],"as":[11],"distinct":[12],"tasks":[13],"in":[14,120],"speech":[15,95],"processing.":[16],"However,":[17],"real-world":[18],"audio":[19],"often":[20],"involves":[21],"both":[22,121],"background":[23],"noise":[24],"overlapping":[26],"speakers,":[27],"motivating":[28],"the":[29,104],"need":[30],"for":[31],"a":[32,70,82],"unified":[33],"solution.":[34],"While":[35],"recent":[36],"approaches":[37,49],"attempted":[39],"to":[40,93,102],"integrate":[41],"SE":[42,78],"SS":[44,80],"within":[45,81],"multi-stage":[46],"architectures,":[47],"these":[48],"typically":[50],"involve":[51],"complex,":[52],"parameter-heavy":[53],"models":[54],"rely":[56],"on":[57],"supervised":[58],"training,":[59],"limiting":[60],"scalability":[61],"generalization.":[63,130],"In":[64],"this":[65],"work,":[66],"we":[67],"propose":[68],"UniVoiceLite,":[69],"lightweight":[71],"unsupervised":[73],"audiovisual":[74],"framework":[75],"that":[76,115],"unifies":[77],"single":[83],"model.":[84],"UniVoiceLite":[85,116],"leverages":[86],"lip":[87],"motion":[88],"facial":[90],"identity":[91],"cues":[92],"guide":[94],"extraction":[96],"employs":[98],"Wasserstein":[99],"distance":[100],"regularization":[101],"stabilize":[103],"latent":[105],"space":[106],"without":[107],"requiring":[108],"paired":[109],"noisy-clean":[110],"data.":[111],"Experimental":[112],"results":[113],"demonstrate":[114],"achieves":[117],"strong":[118],"performance":[119],"noisy":[122],"multi-speaker":[124],"scenarios,":[125],"combining":[126],"efficiency":[127],"with":[128],"robust":[129],"The":[131],"source":[132],"code":[133],"is":[134],"available":[135],"at":[136],"https://github.com/jisoo-o/UniVoiceLite.":[137]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}