{"id":"https://openalex.org/W2577762507","doi":"https://doi.org/10.1109/apsipa.2016.7820732","title":"Audio-visual speech enhancement using deep neural networks","display_name":"Audio-visual speech enhancement using deep neural networks","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2577762507","doi":"https://doi.org/10.1109/apsipa.2016.7820732","mag":"2577762507"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2016.7820732","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2016.7820732","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","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/A5058567113","display_name":"Jen-Cheng Hou","orcid":"https://orcid.org/0000-0002-4010-0220"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Cheng Hou","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073046122","display_name":"Syu\u2010Siang Wang","orcid":"https://orcid.org/0000-0002-2652-5521"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Syu-Siang Wang","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taiwan","Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027128278","display_name":"Ying-Hui Lai","orcid":"https://orcid.org/0000-0003-4120-7289"},"institutions":[{"id":"https://openalex.org/I99908691","display_name":"Yuan Ze University","ror":"https://ror.org/01fv1ds98","country_code":"TW","type":"education","lineage":["https://openalex.org/I99908691"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ying-Hui Lai","raw_affiliation_strings":["Department of Electrical Engineering, Yuan Zn University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Yuan Zn University, Taiwan","institution_ids":["https://openalex.org/I99908691"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077668438","display_name":"Jen\u2010Chun Lin","orcid":"https://orcid.org/0000-0002-9237-4119"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Chun Lin","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082122985","display_name":"Hsiu-Wen Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I35926432","display_name":"Mackay Medical University","ror":"https://ror.org/00t89kj24","country_code":"TW","type":"education","lineage":["https://openalex.org/I35926432"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsiu-Wen Chang","raw_affiliation_strings":["Department of Audiology and Speech language pathology, Mackay Medical College, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Audiology and Speech language pathology, Mackay Medical College, Taiwan","institution_ids":["https://openalex.org/I35926432"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6386,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.92473259,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.996999979019165,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9937000274658203,"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/computer-science","display_name":"Computer science","score":0.8204491138458252},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7158082723617554},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6350024938583374},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.540095329284668},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5339105725288391},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4612089693546295},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4607366919517517},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4466524124145508},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.43692609667778015},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4360966384410858},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3800109028816223},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1432977020740509},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.09589824080467224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8204491138458252},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7158082723617554},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6350024938583374},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.540095329284668},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5339105725288391},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4612089693546295},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4607366919517517},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4466524124145508},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.43692609667778015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4360966384410858},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3800109028816223},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1432977020740509},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.09589824080467224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2016.7820732","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2016.7820732","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6499999761581421,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W650024069","https://openalex.org/W1561742478","https://openalex.org/W1789716261","https://openalex.org/W1897240248","https://openalex.org/W1902027874","https://openalex.org/W1956021273","https://openalex.org/W1969975883","https://openalex.org/W1978380426","https://openalex.org/W1999977067","https://openalex.org/W2000916836","https://openalex.org/W2013608223","https://openalex.org/W2015394094","https://openalex.org/W2044893557","https://openalex.org/W2075731813","https://openalex.org/W2078528584","https://openalex.org/W2092644348","https://openalex.org/W2094461119","https://openalex.org/W2096391593","https://openalex.org/W2096779346","https://openalex.org/W2113131123","https://openalex.org/W2113990625","https://openalex.org/W2121973264","https://openalex.org/W2130563197","https://openalex.org/W2145760110","https://openalex.org/W2147299274","https://openalex.org/W2153894152","https://openalex.org/W2175872006","https://openalex.org/W2183821610","https://openalex.org/W2290548146","https://openalex.org/W2292405593","https://openalex.org/W2334833135","https://openalex.org/W2394498270","https://openalex.org/W2402901296","https://openalex.org/W2405774341","https://openalex.org/W2406954482","https://openalex.org/W2408592723","https://openalex.org/W2487271655","https://openalex.org/W2490695385","https://openalex.org/W2516342150","https://openalex.org/W2978471304","https://openalex.org/W3097096317","https://openalex.org/W3147539069","https://openalex.org/W6633652116","https://openalex.org/W6638249401","https://openalex.org/W6644697353","https://openalex.org/W6711896204","https://openalex.org/W6713117669","https://openalex.org/W6713510121","https://openalex.org/W6713658392","https://openalex.org/W6713796627"],"related_works":["https://openalex.org/W2496295964","https://openalex.org/W2294333436","https://openalex.org/W1976952689","https://openalex.org/W2336887028","https://openalex.org/W3211091508","https://openalex.org/W2547431347","https://openalex.org/W1984921740","https://openalex.org/W2070982348","https://openalex.org/W1911859126","https://openalex.org/W642007152"],"abstract_inverted_index":{"This":[0,64],"paper":[1,65],"proposes":[2],"a":[3],"novel":[4],"framework":[5],"that":[6,103,112],"integrates":[7],"audio":[8,20,45,51,116],"and":[9],"visual":[10,74,83,132],"information":[11,43,84,133],"for":[12],"speech":[13,16,32,61,88,96,137],"enhancement.":[14],"Most":[15],"enhancement":[17,89,97,138],"approaches":[18,56],"consider":[19],"features":[21,75],"only":[22,118],"to":[23,29,34,44,57,85],"design":[24],"filters":[25],"or":[26],"transfer":[27],"functions":[28],"convert":[30],"noisy":[31],"signals":[33],"clean":[35],"ones.":[36],"Visual":[37],"data,":[38,46],"which":[39],"provide":[40],"useful":[41],"complementary":[42],"have":[47],"been":[48],"integrated":[49],"with":[50,108,115],"data":[52],"in":[53,119],"many":[54],"speech-related":[55],"attain":[58],"more":[59],"effective":[60],"processing":[62],"performance.":[63,98],"presents":[66],"our":[67],"investigation":[68],"into":[69,134],"the":[70,73,77,87,104,126,129],"use":[71],"of":[72,76,79,91,106,113,128,131],"motion":[78],"lips":[80],"as":[81],"additional":[82],"improve":[86],"capability":[90],"deep":[92],"neural":[93],"network":[94],"(DNN)":[95],"The":[99],"experimental":[100],"results":[101],"show":[102],"performance":[105],"DNN":[107,114],"audio-visual":[109],"inputs":[110,117],"exceeds":[111],"four":[120],"standardized":[121],"objective":[122],"evaluations,":[123],"thereby":[124],"confirming":[125],"effectiveness":[127],"inclusion":[130],"an":[135],"audio-only":[136],"framework.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
