{"id":"https://openalex.org/W3160005627","doi":"https://doi.org/10.1109/icassp39728.2021.9414263","title":"On The Role of Visual Cues in Audiovisual Speech Enhancement","display_name":"On The Role of Visual Cues in Audiovisual Speech Enhancement","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160005627","doi":"https://doi.org/10.1109/icassp39728.2021.9414263","mag":"3160005627"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414263","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_indexed_in_scopus":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":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":"https://arxiv.org/pdf/2004.12031","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090927958","display_name":"Zakaria Aldeneh","orcid":"https://orcid.org/0000-0003-4599-2448"},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zakaria Aldeneh","raw_affiliation_strings":["Apple, Cupertino, CA, USA"],"affiliations":[{"raw_affiliation_string":"Apple, Cupertino, CA, USA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061966785","display_name":"Anushree Prasanna Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anushree Prasanna Kumar","raw_affiliation_strings":["Apple, Cupertino, CA, USA"],"affiliations":[{"raw_affiliation_string":"Apple, Cupertino, CA, USA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112911728","display_name":"Barry-John Theobald","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Barry-John Theobald","raw_affiliation_strings":["Apple, Cupertino, CA, USA"],"affiliations":[{"raw_affiliation_string":"Apple, Cupertino, CA, USA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009327522","display_name":"Erik Marchi","orcid":"https://orcid.org/0000-0002-5335-6356"},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erik Marchi","raw_affiliation_strings":["Apple, Cupertino, CA, USA"],"affiliations":[{"raw_affiliation_string":"Apple, Cupertino, CA, USA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065814281","display_name":"Sachin Kajarekar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sachin Kajarekar","raw_affiliation_strings":["Apple, Cupertino, CA, USA"],"affiliations":[{"raw_affiliation_string":"Apple, Cupertino, CA, USA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113880378","display_name":"Devang Naik","orcid":"https://orcid.org/0009-0007-7838-1623"},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Devang Naik","raw_affiliation_strings":["Apple, Cupertino, CA, USA"],"affiliations":[{"raw_affiliation_string":"Apple, Cupertino, CA, USA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101807751","display_name":"Ahmed Hussen Abdelaziz","orcid":"https://orcid.org/0000-0001-8027-4666"},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmed Hussen Abdelaziz","raw_affiliation_strings":["Apple, Cupertino, CA, USA"],"affiliations":[{"raw_affiliation_string":"Apple, Cupertino, CA, USA","institution_ids":["https://openalex.org/I4210153776"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.799,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.655846,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":80,"max":82},"biblio":{"volume":null,"issue":null,"first_page":"8423","last_page":"8427"},"is_retracted":false,"is_paratext":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":0.9959,"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":0.9956,"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/viseme","display_name":"Viseme","score":0.7812027},{"id":"https://openalex.org/keywords/sensory-cue","display_name":"Sensory cue","score":0.51664907},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.42003983}],"concepts":[{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.7812027},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7235083},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6358299},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.51664907},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.51441246},{"id":"https://openalex.org/C521332185","wikidata":"https://www.wikidata.org/wiki/Q185816","display_name":"Analogy","level":2,"score":0.4457722},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.42003983},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.36610714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31698036},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.19426748},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08225003},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414263","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_indexed_in_scopus":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":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2004.12031","pdf_url":"https://arxiv.org/pdf/2004.12031","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2004.12031","pdf_url":"https://arxiv.org/pdf/2004.12031","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.42}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":20,"referenced_works":["https://openalex.org/W1495679096","https://openalex.org/W1552314771","https://openalex.org/W1969975883","https://openalex.org/W2115252128","https://openalex.org/W2292743699","https://openalex.org/W2326925005","https://openalex.org/W2515190011","https://openalex.org/W2560747691","https://openalex.org/W2604379605","https://openalex.org/W2889442120","https://openalex.org/W2962866211","https://openalex.org/W2963082324","https://openalex.org/W2964171275","https://openalex.org/W2972381775","https://openalex.org/W2972425344","https://openalex.org/W2972513594","https://openalex.org/W3099202502","https://openalex.org/W3123318516","https://openalex.org/W4253928870","https://openalex.org/W4289665794"],"related_works":["https://openalex.org/W4212815228","https://openalex.org/W2777626350","https://openalex.org/W2469799552","https://openalex.org/W2392206215","https://openalex.org/W2365201483","https://openalex.org/W2355561779","https://openalex.org/W2352407775","https://openalex.org/W2186567693","https://openalex.org/W1852407300","https://openalex.org/W108701362"],"abstract_inverted_index":{"We":[0,35,81],"present":[1],"an":[2,5],"introspection":[3],"of":[4,30,58,62,85,105],"audiovisual":[6,19,106],"speech":[7,20,33,46,79,107,122],"enhancement":[8,21,108],"model.":[9],"In":[10],"particular,":[11],"we":[12],"focus":[13],"on":[14],"interpreting":[15],"how":[16,111],"a":[17],"neural":[18],"model":[22],"uses":[23],"visual":[24,38,53,69,78,88,94,121],"cues":[25,39],"to":[26,96],"improve":[27],"the":[28,31,56,67,83,86],"quality":[29],"target":[32],"signal.":[34],"show":[36],"that":[37,66],"provide":[40,100],"not":[41],"only":[42],"high-level":[43],"information":[44,54],"about":[45,55],"activity,":[47],"i.e.,":[48],"speech/silence,":[49],"but":[50],"also":[51],"fine-grained":[52],"place":[57],"articulation.":[59],"One":[60],"byproduct":[61],"this":[63],"finding":[64],"is":[65],"learned":[68,87],"embeddings":[70,89],"can":[71,114],"be":[72,115],"used":[73,116],"as":[74],"features":[75],"for":[76,90,117,120],"other":[77],"applications.":[80,123],"demonstrate":[82,110],"effectiveness":[84],"classifying":[91],"visemes":[92],"(the":[93],"analogy":[95],"phonemes).":[97],"Our":[98],"results":[99],"insight":[101],"into":[102],"important":[103],"aspects":[104],"and":[109],"such":[112],"models":[113],"self-supervision":[118],"tasks":[119]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3160005627","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2025-04-20T17:53:50.042687","created_date":"2021-05-24"}