{"id":"https://openalex.org/W4392904258","doi":"https://doi.org/10.1109/icassp48485.2024.10446625","title":"AV2WAV: Diffusion-Based Re-Synthesis from Continuous Self-Supervised Features for Audio-Visual Speech Enhancement","display_name":"AV2WAV: Diffusion-Based Re-Synthesis from Continuous Self-Supervised Features for Audio-Visual Speech Enhancement","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904258","doi":"https://doi.org/10.1109/icassp48485.2024.10446625"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446625","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446625","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5049062211","display_name":"Ju-Chieh Chou","orcid":null},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ju-Chieh Chou","raw_affiliation_strings":["Toyota Technological Institute,Chicago","Toyota Technological Institute, Chicago"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute,Chicago","institution_ids":["https://openalex.org/I160992636"]},{"raw_affiliation_string":"Toyota Technological Institute, Chicago","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072923563","display_name":"Chung-Ming Chien","orcid":null},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chung-Ming Chien","raw_affiliation_strings":["Toyota Technological Institute,Chicago","Toyota Technological Institute, Chicago"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute,Chicago","institution_ids":["https://openalex.org/I160992636"]},{"raw_affiliation_string":"Toyota Technological Institute, Chicago","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015602781","display_name":"Karen Livescu","orcid":"https://orcid.org/0000-0003-4962-946X"},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karen Livescu","raw_affiliation_strings":["Toyota Technological Institute,Chicago","Toyota Technological Institute, Chicago"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute,Chicago","institution_ids":["https://openalex.org/I160992636"]},{"raw_affiliation_string":"Toyota Technological Institute, Chicago","institution_ids":["https://openalex.org/I160992636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5049062211"],"corresponding_institution_ids":["https://openalex.org/I160992636"],"apc_list":null,"apc_paid":null,"fwci":2.9884,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.91636773,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10806","last_page":"10810"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9944000244140625,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9902999997138977,"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/computer-science","display_name":"Computer science","score":0.7735574841499329},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7613130807876587},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5954277515411377},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5693176984786987},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5205339193344116},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.49115821719169617},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.4657030701637268},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43345797061920166},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.42835062742233276},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.25722843408584595}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7735574841499329},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7613130807876587},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5954277515411377},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5693176984786987},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5205339193344116},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.49115821719169617},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.4657030701637268},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43345797061920166},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.42835062742233276},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.25722843408584595},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446625","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446625","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":34,"referenced_works":["https://openalex.org/W349236604","https://openalex.org/W1522301498","https://openalex.org/W2015143272","https://openalex.org/W2788241093","https://openalex.org/W2808631503","https://openalex.org/W2891205112","https://openalex.org/W2963192057","https://openalex.org/W2964058413","https://openalex.org/W2964171275","https://openalex.org/W3121370741","https://openalex.org/W3140429000","https://openalex.org/W3182657421","https://openalex.org/W4221153068","https://openalex.org/W4224933800","https://openalex.org/W4226403810","https://openalex.org/W4281820413","https://openalex.org/W4297841641","https://openalex.org/W4311000453","https://openalex.org/W4312337341","https://openalex.org/W4319862437","https://openalex.org/W4372260337","https://openalex.org/W4372266927","https://openalex.org/W4379474007","https://openalex.org/W4385478414","https://openalex.org/W4386076005","https://openalex.org/W6631190155","https://openalex.org/W6754420807","https://openalex.org/W6780226713","https://openalex.org/W6782760101","https://openalex.org/W6783713337","https://openalex.org/W6810168380","https://openalex.org/W6847363464","https://openalex.org/W6853302197","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W258725851","https://openalex.org/W2135485548","https://openalex.org/W2373767407","https://openalex.org/W2187949121","https://openalex.org/W1980045272","https://openalex.org/W2376606440","https://openalex.org/W2251439150","https://openalex.org/W2568425241","https://openalex.org/W1127445803","https://openalex.org/W3030102128"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,16,55,131],"systems":[2],"are":[3,30],"typically":[4],"trained":[5],"using":[6,81],"pairs":[7,146],"of":[8,43,65,73,159],"clean":[9,24,60,75],"and":[10,38,86,118,163,168],"noisy":[11],"speech.":[12],"In":[13,45],"audio-visual":[14,28,53,79],"speech":[15,54,61,76,101,130,176],"(AVSE),":[17],"there":[18],"is":[19,169],"not":[20],"as":[21],"much":[22],"ground-truth":[23],"data":[25],"available;":[26],"most":[27],"datasets":[29],"collected":[31],"in":[32,157,171,177],"real-world":[33,66],"environments":[34],"with":[35,105],"background":[36],"noise":[37],"reverberation,":[39],"hampering":[40],"the":[41,63,126,140,149,174,178],"development":[42],"AVSE.":[44],"this":[46,93,122],"work,":[47],"we":[48],"introduce":[49],"AV2Wav,":[50],"a":[51,71,82,89,134,154,164],"resynthesis-based":[52],"approach":[56,152],"that":[57],"can":[58,128],"generate":[59,96],"despite":[62],"challenges":[64],"training":[67],"data.":[68],"We":[69,108,137],"obtain":[70],"subset":[72,94],"nearly":[74],"from":[77,103],"an":[78],"corpus":[80],"neural":[83],"quality":[84,172],"estimator,":[85],"then":[87],"train":[88],"diffusion":[90,141],"model":[91,127,142],"on":[92,99,143],"to":[95,115,147,173],"waveforms":[97],"conditioned":[98],"continuous":[100,110],"representations":[102,114],"AV-HuBERT":[104],"noise-robust":[106],"training.":[107],"use":[109],"rather":[111],"than":[112,133],"discrete":[113],"retain":[116],"prosody":[117],"speaker":[119],"information.":[120],"With":[121],"vocoding":[123],"task":[124],"alone,":[125],"perform":[129],"better":[132],"masking-based":[135,155],"baseline.":[136],"further":[138],"fine-tune":[139],"clean/noisy":[144],"utterance":[145],"improve":[148],"performance.":[150],"Our":[151],"outperforms":[153],"baseline":[156],"terms":[158],"both":[160],"automatic":[161],"metrics":[162],"human":[165],"listening":[166,179],"test":[167],"close":[170],"target":[175],"test.":[180],"<sup":[181],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[182],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}