{"id":"https://openalex.org/W4221164771","doi":"https://doi.org/10.1109/icassp43922.2022.9746401","title":"The Impact of Removing Head Movements on Audio-Visual Speech Enhancement","display_name":"The Impact of Removing Head Movements on Audio-Visual Speech Enhancement","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221164771","doi":"https://doi.org/10.1109/icassp43922.2022.9746401"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746401","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2202.00538","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044584521","display_name":"Zhiqi Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Zhiqi Kang","raw_affiliation_strings":["Inria Grenoble & Univ. Grenoble Alpes,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria Grenoble & Univ. Grenoble Alpes,France","institution_ids":["https://openalex.org/I4210101348","https://openalex.org/I899635006"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062612015","display_name":"Mostafa Sadeghi","orcid":"https://orcid.org/0000-0002-0272-8017"},"institutions":[{"id":"https://openalex.org/I4210127166","display_name":"Centre Inria de l'Universit\u00e9 de Lorraine","ror":"https://ror.org/03fcjvn64","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210127166"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mostafa Sadeghi","raw_affiliation_strings":["Inria Nancy Grand-Est,France","Speech Modeling for Facilitating Oral-Based Communication"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria Nancy Grand-Est,France","institution_ids":["https://openalex.org/I4210127166"]},{"raw_affiliation_string":"Speech Modeling for Facilitating Oral-Based Communication","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078307335","display_name":"Radu Horaud","orcid":"https://orcid.org/0000-0001-5232-024X"},"institutions":[{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Radu Horaud","raw_affiliation_strings":["Inria Grenoble & Univ. Grenoble Alpes,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria Grenoble & Univ. Grenoble Alpes,France","institution_ids":["https://openalex.org/I4210101348","https://openalex.org/I899635006"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066621495","display_name":"Xavier Alameda-Pineda","orcid":"https://orcid.org/0000-0002-5354-1084"},"institutions":[{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Xavier Alameda-Pineda","raw_affiliation_strings":["Inria Grenoble & Univ. Grenoble Alpes,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria Grenoble & Univ. Grenoble Alpes,France","institution_ids":["https://openalex.org/I4210101348","https://openalex.org/I899635006"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055065049","display_name":"Jacob Donley","orcid":"https://orcid.org/0000-0002-8401-798X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jacob Donley","raw_affiliation_strings":["Reality Labs Research,Redmond,WA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reality Labs Research,Redmond,WA,USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080751032","display_name":"Anurag Kumar","orcid":"https://orcid.org/0000-0002-1164-144X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anurag Kumar","raw_affiliation_strings":["Reality Labs Research,Redmond,WA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reality Labs Research,Redmond,WA,USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7302","last_page":"7306"},"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/T11448","display_name":"Face recognition and analysis","score":0.998199999332428,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9853000044822693,"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/pesq","display_name":"PESQ","score":0.8213609457015991},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7691532373428345},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7217857241630554},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6654545068740845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5841467380523682},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4885424077510834},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4840935468673706},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4625180959701538},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4573504328727722},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4536757171154022},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.426133394241333},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.4151359498500824},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.37598344683647156},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3531050682067871},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.244498610496521},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.08265671133995056}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.8213609457015991},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7691532373428345},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7217857241630554},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6654545068740845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5841467380523682},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4885424077510834},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4840935468673706},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4625180959701538},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4573504328727722},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4536757171154022},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.426133394241333},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.4151359498500824},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.37598344683647156},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3531050682067871},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.244498610496521},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.08265671133995056},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746401","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2202.00538","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.00538","pdf_url":"https://arxiv.org/pdf/2202.00538","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:HAL:hal-03551610v2","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-03551610","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing, IEEE Signal Processing Society, May 2022, Singapore, Singapore. pp.1-5, ⟨10.1109/ICASSP43922.2022.9746401⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2202.00538","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.00538","pdf_url":"https://arxiv.org/pdf/2202.00538","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5899999737739563}],"awards":[{"id":"https://openalex.org/G1041279674","display_name":"MIAI @ Grenoble Alpes","funder_award_id":"ANR-19-P3IA-0003","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1959608418","https://openalex.org/W2107037917","https://openalex.org/W2141998673","https://openalex.org/W2157321274","https://openalex.org/W2194775991","https://openalex.org/W2788241093","https://openalex.org/W2949662773","https://openalex.org/W2963082324","https://openalex.org/W2964171275","https://openalex.org/W2965390715","https://openalex.org/W2972513594","https://openalex.org/W3015791137","https://openalex.org/W3016011581","https://openalex.org/W3033703941","https://openalex.org/W3035169015","https://openalex.org/W3099284785","https://openalex.org/W3100968126","https://openalex.org/W3104792420","https://openalex.org/W3127511859","https://openalex.org/W3136499730","https://openalex.org/W3137758952","https://openalex.org/W3160658686","https://openalex.org/W3195345689","https://openalex.org/W3209141406","https://openalex.org/W6640963894","https://openalex.org/W6773882011","https://openalex.org/W6785473800","https://openalex.org/W6802983977","https://openalex.org/W7005955626"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W3016109656","https://openalex.org/W1973895194","https://openalex.org/W3135613579","https://openalex.org/W4388016426","https://openalex.org/W1980687383","https://openalex.org/W4386746628","https://openalex.org/W2546593254","https://openalex.org/W2166831097","https://openalex.org/W3209446892"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,38,80,84,98,119],"impact":[4],"of":[5,40,83,100,121],"head":[6,19],"movements":[7,20],"on":[8,45,71,105],"audio-visual":[9,95],"speech":[10],"enhancement":[11],"(AVSE).":[12],"Although":[13],"being":[14],"a":[15,72,92,124],"common":[16],"conversational":[17],"feature,":[18],"have":[21],"been":[22],"ignored":[23],"by":[24,123],"past":[25],"and":[26,48,87,103,112],"recent":[27],"studies:":[28],"they":[29,35],"challenge":[30],"today\u2019s":[31],"learning-based":[32],"methods":[33],"as":[34],"often":[36],"degrade":[37],"performance":[39,120],"models":[41],"that":[42,116],"are":[43],"trained":[44],"clean,":[46],"frontal,":[47],"steady":[49],"face":[50,61],"images.":[51],"To":[52],"alleviate":[53],"this":[54],"problem,":[55],"we":[56,88,114],"propose":[57],"to":[58],"use":[59],"robust":[60],"frontalization":[62],"(RFF)":[63],"in":[64],"combination":[65],"with":[66,91],"an":[67],"AVSE":[68,122],"method":[69],"based":[70,104],"variational":[73],"auto-encoder":[74],"(VAE)":[75],"model.":[76],"We":[77],"briefly":[78],"describe":[79],"basic":[81],"ingredients":[82],"proposed":[85],"pipeline":[86],"perform":[89],"experiments":[90],"recently":[93],"released":[94],"dataset.":[96],"In":[97],"light":[99],"these":[101],"experiments,":[102],"three":[106],"standard":[107],"metrics,":[108],"namely":[109],"STOI,":[110],"PESQ":[111],"SI-SDR,":[113],"conclude":[115],"RFF":[117],"improves":[118],"considerable":[125],"margin.":[126],"1":[129]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}