{"id":"https://openalex.org/W4319586313","doi":"https://doi.org/10.1109/iscslp57327.2022.10038268","title":"Multi-Task Joint Learning for Embedding Aware Audio-Visual Speech Enhancement","display_name":"Multi-Task Joint Learning for Embedding Aware Audio-Visual Speech Enhancement","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4319586313","doi":"https://doi.org/10.1109/iscslp57327.2022.10038268"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp57327.2022.10038268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10038268","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5103325598","display_name":"Chenxi Wang","orcid":"https://orcid.org/0009-0003-1457-5120"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenxi Wang","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100442529","display_name":"Hang Chen","orcid":"https://orcid.org/0000-0002-9011-4110"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Chen","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059859891","display_name":"Baocai Yin","orcid":"https://orcid.org/0000-0002-4164-6647"},"institutions":[{"id":"https://openalex.org/I39774598","display_name":"Hefei University","ror":"https://ror.org/01f5rdf64","country_code":"CN","type":"education","lineage":["https://openalex.org/I39774598"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baocai Yin","raw_affiliation_strings":["iFlytek,Hefei,China","iFlytek, Hefei, China"],"affiliations":[{"raw_affiliation_string":"iFlytek,Hefei,China","institution_ids":["https://openalex.org/I39774598"]},{"raw_affiliation_string":"iFlytek, Hefei, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076812698","display_name":"Jia Pan","orcid":"https://orcid.org/0000-0001-9003-2054"},"institutions":[{"id":"https://openalex.org/I39774598","display_name":"Hefei University","ror":"https://ror.org/01f5rdf64","country_code":"CN","type":"education","lineage":["https://openalex.org/I39774598"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Pan","raw_affiliation_strings":["iFlytek,Hefei,China","iFlytek, Hefei, China"],"affiliations":[{"raw_affiliation_string":"iFlytek,Hefei,China","institution_ids":["https://openalex.org/I39774598"]},{"raw_affiliation_string":"iFlytek, Hefei, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103325598"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.2455,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.4549763,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"255","last_page":"259"},"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":0.9959999918937683,"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":0.9908000230789185,"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/embedding","display_name":"Embedding","score":0.774530291557312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7701413035392761},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.7339528799057007},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.684023916721344},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6471884846687317},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5709192156791687},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5560756325721741},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4746730327606201},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46195343136787415},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3263435959815979},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.19747194647789001},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.12090367078781128},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08145421743392944}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.774530291557312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7701413035392761},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7339528799057007},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.684023916721344},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6471884846687317},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5709192156791687},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5560756325721741},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4746730327606201},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46195343136787415},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3263435959815979},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.19747194647789001},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.12090367078781128},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08145421743392944},{"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/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp57327.2022.10038268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10038268","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6000000238418579}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W190004713","https://openalex.org/W258661521","https://openalex.org/W1552314771","https://openalex.org/W1558945660","https://openalex.org/W1902954812","https://openalex.org/W1968939597","https://openalex.org/W1974387177","https://openalex.org/W1980741455","https://openalex.org/W1995536493","https://openalex.org/W2002621203","https://openalex.org/W2015394094","https://openalex.org/W2029199293","https://openalex.org/W2044893557","https://openalex.org/W2060630096","https://openalex.org/W2062652351","https://openalex.org/W2087681821","https://openalex.org/W2099731107","https://openalex.org/W2115252128","https://openalex.org/W2121973264","https://openalex.org/W2128653836","https://openalex.org/W2141998673","https://openalex.org/W2157331557","https://openalex.org/W2159202424","https://openalex.org/W2194775991","https://openalex.org/W2405774341","https://openalex.org/W2788241093","https://openalex.org/W2900292050","https://openalex.org/W2963082324","https://openalex.org/W2964171275","https://openalex.org/W2991015288","https://openalex.org/W3004146833","https://openalex.org/W3008400075","https://openalex.org/W3105483368","https://openalex.org/W3126260881","https://openalex.org/W3168662520","https://openalex.org/W4210478401","https://openalex.org/W4237742002","https://openalex.org/W4297841411","https://openalex.org/W4308668055","https://openalex.org/W6677618333"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W4375869169","https://openalex.org/W2597829360","https://openalex.org/W2037635165","https://openalex.org/W3000153094","https://openalex.org/W2542062716","https://openalex.org/W2738829087","https://openalex.org/W2231565466","https://openalex.org/W3043214604","https://openalex.org/W1505346162"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,64],"propose":[4],"a":[5],"multi-task":[6,123],"joint":[7,125],"learning":[8,75,126],"scheme":[9],"to":[10],"improve":[11],"embedding":[12,34,42,67,104,116],"aware":[13],"audio-visual":[14],"speech":[15,47,130],"enhancement":[16,37,70],"by":[17,53,95],"adopting":[18],"the":[19,22,27,31,40,54,58,66,74,78,82,86,91,101,106,114,118,122],"phone":[20,59,83],"and":[21,36,48,51,57,69,85,121,132],"articulation":[23,55],"place":[24,56,87],"together":[25],"as":[26],"classification":[28],"targets":[29],"during":[30],"training":[32],"of":[33],"extractor":[35,68],"network.":[38],"Firstly,":[39],"multimodal":[41,103],"is":[43,110],"extracted":[44],"from":[45],"noisy":[46],"lip":[49],"frames,":[50],"supervised":[52],"label":[60],"levels":[61],"together.":[62],"Next,":[63],"train":[65],"network":[71],"jointly":[72],"where":[73],"objects":[76],"include":[77],"ideal":[79],"ratio":[80],"mask,":[81],"posteriori":[84],"posteriori.":[88],"Experiments":[89],"on":[90],"TCD-TIMIT":[92],"corpus":[93],"corrupted":[94],"simulated":[96],"additive":[97],"noises":[98],"show":[99],"that":[100],"proposed":[102],"at":[105,117],"multi-scale":[107],"class":[108],"level":[109,120],"more":[111],"effective":[112],"than":[113],"previous":[115],"place/phone":[119],"based":[124],"framework":[127],"further":[128],"improves":[129],"quality":[131],"intelligibility.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
