{"id":"https://openalex.org/W4372260127","doi":"https://doi.org/10.1109/icassp49357.2023.10096390","title":"LA-VOCE: LOW-SNR Audio-Visual Speech Enhancement Using Neural Vocoders","display_name":"LA-VOCE: LOW-SNR Audio-Visual Speech Enhancement Using Neural Vocoders","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260127","doi":"https://doi.org/10.1109/icassp49357.2023.10096390"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5013092421","display_name":"Rodrigo Mira","orcid":"https://orcid.org/0000-0002-9493-3842"},"institutions":[{"id":"https://openalex.org/I4210109636","display_name":"NIHR Imperial Biomedical Research Centre","ror":"https://ror.org/01kmhx639","country_code":"GB","type":"facility","lineage":["https://openalex.org/I34931013","https://openalex.org/I4210109636"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rodrigo Mira","raw_affiliation_strings":["iBUG, Imperial College London,UK","iBUG, Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iBUG, Imperial College London,UK","institution_ids":["https://openalex.org/I47508984","https://openalex.org/I4210109636"]},{"raw_affiliation_string":"iBUG, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040562171","display_name":"Buye Xu","orcid":"https://orcid.org/0000-0002-3027-7567"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Buye Xu","raw_affiliation_strings":["Meta Reality Labs Research,USA","Meta Reality Labs Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research,USA","institution_ids":["https://openalex.org/I4210128585"]},{"raw_affiliation_string":"Meta Reality Labs Research, USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055065049","display_name":"Jacob Donley","orcid":"https://orcid.org/0000-0002-8401-798X"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Donley","raw_affiliation_strings":["Meta Reality Labs Research,USA","Meta Reality Labs Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research,USA","institution_ids":["https://openalex.org/I4210128585"]},{"raw_affiliation_string":"Meta Reality Labs Research, USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080751032","display_name":"Anurag Kumar","orcid":"https://orcid.org/0000-0002-1164-144X"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anurag Kumar","raw_affiliation_strings":["Meta Reality Labs Research,USA","Meta Reality Labs Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research,USA","institution_ids":["https://openalex.org/I4210128585"]},{"raw_affiliation_string":"Meta Reality Labs Research, USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009475700","display_name":"Stavros Petridis","orcid":"https://orcid.org/0000-0001-7478-9479"},"institutions":[{"id":"https://openalex.org/I4210109636","display_name":"NIHR Imperial Biomedical Research Centre","ror":"https://ror.org/01kmhx639","country_code":"GB","type":"facility","lineage":["https://openalex.org/I34931013","https://openalex.org/I4210109636"]},{"id":"https://openalex.org/I4210111288","display_name":"Meta (United Kingdom)","ror":"https://ror.org/020ye1821","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210111288","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stavros Petridis","raw_affiliation_strings":["iBUG, Imperial College London,UK","iBUG, Imperial College London, UK","Meta, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iBUG, Imperial College London,UK","institution_ids":["https://openalex.org/I47508984","https://openalex.org/I4210109636"]},{"raw_affiliation_string":"iBUG, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Meta, UK","institution_ids":["https://openalex.org/I4210111288"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108520440","display_name":"Vamsi Krishna Ithapu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vamsi Krishna Ithapu","raw_affiliation_strings":["Meta Reality Labs Research,USA","Meta Reality Labs Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research,USA","institution_ids":["https://openalex.org/I4210128585"]},{"raw_affiliation_string":"Meta Reality Labs Research, USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016033078","display_name":"Maja Panti\u0107","orcid":"https://orcid.org/0000-0002-3620-5986"},"institutions":[{"id":"https://openalex.org/I4210109636","display_name":"NIHR Imperial Biomedical Research Centre","ror":"https://ror.org/01kmhx639","country_code":"GB","type":"facility","lineage":["https://openalex.org/I34931013","https://openalex.org/I4210109636"]},{"id":"https://openalex.org/I4210111288","display_name":"Meta (United Kingdom)","ror":"https://ror.org/020ye1821","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210111288","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Maja Pantic","raw_affiliation_strings":["iBUG, Imperial College London,UK","iBUG, Imperial College London, UK","Meta, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iBUG, Imperial College London,UK","institution_ids":["https://openalex.org/I47508984","https://openalex.org/I4210109636"]},{"raw_affiliation_string":"iBUG, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Meta, UK","institution_ids":["https://openalex.org/I4210111288"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4019,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.89624861,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"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":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":0.9943000078201294,"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":0.9923999905586243,"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":0.8132612705230713},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7283435463905334},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7161654829978943},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6140769720077515},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5164914131164551},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.4954310655593872},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4338165521621704},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37438854575157166},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.17386621236801147},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.09780272841453552}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8132612705230713},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7283435463905334},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7161654829978943},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6140769720077515},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5164914131164551},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4954310655593872},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4338165521621704},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37438854575157166},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.17386621236801147},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.09780272841453552},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2015143272","https://openalex.org/W2067295501","https://openalex.org/W2107860279","https://openalex.org/W2120847449","https://openalex.org/W2194775991","https://openalex.org/W2516001803","https://openalex.org/W2593414223","https://openalex.org/W2788241093","https://openalex.org/W2908510526","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2963082324","https://openalex.org/W2963263347","https://openalex.org/W2963654155","https://openalex.org/W2964110616","https://openalex.org/W2964167449","https://openalex.org/W2972404066","https://openalex.org/W2991361823","https://openalex.org/W3023846453","https://openalex.org/W3036367741","https://openalex.org/W3037038648","https://openalex.org/W3092028330","https://openalex.org/W3096643087","https://openalex.org/W3097906045","https://openalex.org/W3097945073","https://openalex.org/W3099330747","https://openalex.org/W3157840621","https://openalex.org/W3162293946","https://openalex.org/W3163287738","https://openalex.org/W3182657421","https://openalex.org/W3215615641","https://openalex.org/W4221153068","https://openalex.org/W4289665794","https://openalex.org/W4296069328","https://openalex.org/W4307286264","https://openalex.org/W4312337341","https://openalex.org/W4385245566","https://openalex.org/W6687506355","https://openalex.org/W6726497184","https://openalex.org/W6739901393","https://openalex.org/W6749863746","https://openalex.org/W6757817989","https://openalex.org/W6768469449","https://openalex.org/W6776011093","https://openalex.org/W6783867762","https://openalex.org/W6810168380","https://openalex.org/W6810661184"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2088854863","https://openalex.org/W2011227383","https://openalex.org/W2065606036","https://openalex.org/W1976719989","https://openalex.org/W2942893872","https://openalex.org/W3179495260","https://openalex.org/W3127543252","https://openalex.org/W3211091508"],"abstract_inverted_index":{"Audio-visual":[0],"speech":[1,7,36,49,72,91,136],"enhancement":[2,73],"aims":[3],"to":[4,31,55,59,70,127,129,147],"extract":[5],"clean":[6,62],"from":[8,88],"a":[9,81,93,104],"noisy":[10,89,153],"environment":[11],"by":[12],"leveraging":[13],"not":[14],"only":[15],"the":[16,21,40,61],"audio":[17,102],"itself":[18],"but":[19],"also":[20],"target":[22],"speaker\u2019s":[23],"lip":[24],"movements.":[25],"This":[26],"approach":[27,84],"has":[28],"been":[29],"shown":[30],"yield":[32],"improvements":[33],"over":[34],"audio-only":[35],"enhancement,":[37],"particularly":[38,150],"for":[39],"removal":[41],"of":[42,116,132],"interfering":[43],"speech.":[44],"Despite":[45],"recent":[46],"advances":[47],"in":[48,66],"synthesis,":[50],"most":[51],"audio-visual":[52,90],"approaches":[53],"continue":[54],"use":[56],"spectral":[57],"mapping/masking":[58],"reproduce":[60],"audio,":[63],"often":[64],"resulting":[65],"visual":[67],"backbones":[68],"added":[69],"existing":[71,144],"architectures.":[74],"In":[75],"this":[76],"work,":[77],"we":[78],"propose":[79],"LA-VocE,":[80],"new":[82],"two-stage":[83],"that":[85,141],"predicts":[86],"mel-spectrograms":[87],"via":[92],"transformer-based":[94],"architecture,":[95],"and":[96,110,118,122,135],"then":[97],"converts":[98],"them":[99],"into":[100],"waveform":[101],"using":[103],"neural":[105],"vocoder":[106],"(HiFi-GAN).":[107],"We":[108],"train":[109],"evaluate":[111],"our":[112,124],"framework":[113],"on":[114],"thousands":[115],"speakers":[117],"11+":[119],"different":[120,130],"languages,":[121],"study":[123],"model\u2019s":[125],"ability":[126],"adapt":[128],"levels":[131],"background":[133],"noise":[134],"interference.":[137],"Our":[138],"experiments":[139],"show":[140],"LA-VocE":[142],"outperforms":[143],"methods":[145],"according":[146],"multiple":[148],"metrics,":[149],"under":[151],"very":[152],"scenarios.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}