{"id":"https://openalex.org/W3160310387","doi":"https://doi.org/10.1109/icassp39728.2021.9414053","title":"Vset: A Multimodal Transformer for Visual Speech Enhancement","display_name":"Vset: A Multimodal Transformer for Visual Speech Enhancement","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160310387","doi":"https://doi.org/10.1109/icassp39728.2021.9414053","mag":"3160310387"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5035437944","display_name":"Karthik Ramesh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Karthik Ramesh","raw_affiliation_strings":["Huawei Noah\u2019s Ark Lab","Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]},{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107981608","display_name":"Chao Xing","orcid":"https://orcid.org/0000-0003-1120-8803"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Chao Xing","raw_affiliation_strings":["Huawei Noah\u2019s Ark Lab","Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]},{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006131727","display_name":"Wupeng Wang","orcid":"https://orcid.org/0009-0000-5360-2054"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Wupeng Wang","raw_affiliation_strings":["Huawei Noah\u2019s Ark Lab","Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]},{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391452","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-1964-3984"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Center for Speech and Language Technology (CSLT), Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technology (CSLT), Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100768162","display_name":"Xiao Chen","orcid":"https://orcid.org/0000-0002-7634-9319"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Xiao Chen","raw_affiliation_strings":["Huawei Noah\u2019s Ark Lab","Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]},{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6658","last_page":"6662"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9869999885559082,"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/T11309","display_name":"Music and Audio Processing","score":0.9836000204086304,"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/transformer","display_name":"Transformer","score":0.7270466089248657},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7042644023895264},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5942233800888062},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4505668878555298},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.42541804909706116},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.41438037157058716},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3713850975036621},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18497878313064575},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.16718164086341858},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.13589715957641602},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08315163850784302}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7270466089248657},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7042644023895264},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5942233800888062},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4505668878555298},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.42541804909706116},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.41438037157058716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3713850975036621},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18497878313064575},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.16718164086341858},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.13589715957641602},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08315163850784302},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/icassp39728.2021.9414053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1882423120","https://openalex.org/W1973216748","https://openalex.org/W1977768866","https://openalex.org/W1981527043","https://openalex.org/W2014621385","https://openalex.org/W2015143272","https://openalex.org/W2015394094","https://openalex.org/W2038548569","https://openalex.org/W2081144555","https://openalex.org/W2107878631","https://openalex.org/W2341528187","https://openalex.org/W2531409750","https://openalex.org/W2605589342","https://openalex.org/W2626778328","https://openalex.org/W2788241093","https://openalex.org/W2963082324","https://openalex.org/W2971871542","https://openalex.org/W3015785290","https://openalex.org/W3035810926","https://openalex.org/W3101998545","https://openalex.org/W3123318516","https://openalex.org/W4288103436","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6749863746","https://openalex.org/W6750169759","https://openalex.org/W6767852069","https://openalex.org/W6768074986","https://openalex.org/W6779804293"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2393726419"],"abstract_inverted_index":{"The":[0],"transformer":[1,18,57],"architecture":[2],"has":[3,19],"shown":[4],"great":[5],"capability":[6],"in":[7,14,23],"learning":[8,64],"long-term":[9,66],"dependency":[10,67],"and":[11,52,71,83,86],"works":[12],"well":[13],"multiple":[15],"domains.":[16],"However,":[17],"been":[20],"less":[21],"considered":[22],"audio-visual":[24,56],"speech":[25,36],"enhancement":[26,37],"(AVSE)":[27],"research,":[28],"partly":[29],"due":[30],"to":[31],"the":[32,65,81],"convention":[33],"that":[34,54,88],"treats":[35],"as":[38],"a":[39,95],"short-time":[40],"signal":[41],"processing":[42],"task.":[43],"In":[44],"this":[45,49,75],"paper,":[46],"we":[47],"challenge":[48],"common":[50],"belief":[51],"show":[53,87],"an":[55],"can":[58],"significantly":[59],"improve":[60],"AVSE":[61,78],"performance,":[62],"by":[63,94],"of":[68],"both":[69],"intra-modality":[70],"inter-modality.":[72],"We":[73],"test":[74],"new":[76],"transformer-based":[77],"model":[79],"on":[80],"GRID":[82],"AVSpeech":[84],"datasets,":[85],"it":[89],"beats":[90],"several":[91],"state-of-the-art":[92],"models":[93],"large":[96],"margin.":[97]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
