{"id":"https://openalex.org/W2788241093","doi":"https://doi.org/10.1109/tetci.2017.2784878","title":"Audio-Visual Speech Enhancement Using Multimodal Deep Convolutional Neural Networks","display_name":"Audio-Visual Speech Enhancement Using Multimodal Deep Convolutional Neural Networks","publication_year":2018,"publication_date":"2018-03-23","ids":{"openalex":"https://openalex.org/W2788241093","doi":"https://doi.org/10.1109/tetci.2017.2784878","mag":"2788241093"},"language":"en","primary_location":{"id":"doi:10.1109/tetci.2017.2784878","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2017.2784878","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","raw_type":"journal-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/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":true,"raw_author_name":"Jen-Cheng Hou","raw_affiliation_strings":["Research Center for Information Technology Innovation, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Taipei, 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"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Syu-Siang Wang","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"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/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]},{"id":"https://openalex.org/I4210087697","display_name":"National Yang Ming University Hospital","ror":"https://ror.org/003xdw211","country_code":"TW","type":"healthcare","lineage":["https://openalex.org/I4210087697"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ying-Hui Lai","raw_affiliation_strings":["Department of Biomedical Engineering, National Yang-Ming University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Biomedical Engineering, National Yang-Ming University, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210087697","https://openalex.org/I148366613"]}]},{"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, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Taipei, 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, New Taipei City, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Audiology and Speech language pathology, Mackay Medical College, New Taipei City, 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, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5058567113"],"corresponding_institution_ids":["https://openalex.org/I4210086894"],"apc_list":null,"apc_paid":null,"fwci":19.0857,"has_fulltext":false,"cited_by_count":245,"citation_normalized_percentile":{"value":0.9960201,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"2","issue":"2","first_page":"117","last_page":"128"},"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":0.9979000091552734,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9944000244140625,"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/computer-science","display_name":"Computer science","score":0.8218979835510254},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6765044927597046},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6491997241973877},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6161584258079529},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5521364808082581},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49321573972702026},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.48522496223449707},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4804946184158325},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.451643705368042},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45157331228256226},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.45066890120506287},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3041381537914276},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.2546883821487427},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.11758705973625183}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8218979835510254},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6765044927597046},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6491997241973877},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6161584258079529},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5521364808082581},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49321573972702026},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.48522496223449707},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4804946184158325},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.451643705368042},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45157331228256226},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.45066890120506287},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3041381537914276},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2546883821487427},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.11758705973625183},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tetci.2017.2784878","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2017.2784878","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":101,"referenced_works":["https://openalex.org/W142945732","https://openalex.org/W650024069","https://openalex.org/W1495679096","https://openalex.org/W1503933356","https://openalex.org/W1552314771","https://openalex.org/W1561742478","https://openalex.org/W1565194362","https://openalex.org/W1573024203","https://openalex.org/W1603327663","https://openalex.org/W1686810756","https://openalex.org/W1789716261","https://openalex.org/W1897240248","https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W1956021273","https://openalex.org/W1969975883","https://openalex.org/W1978380426","https://openalex.org/W1990503025","https://openalex.org/W1999454387","https://openalex.org/W1999977067","https://openalex.org/W2000916836","https://openalex.org/W2015394094","https://openalex.org/W2038010270","https://openalex.org/W2044893557","https://openalex.org/W2055228011","https://openalex.org/W2065286263","https://openalex.org/W2075731813","https://openalex.org/W2076528530","https://openalex.org/W2078528584","https://openalex.org/W2078639319","https://openalex.org/W2092644348","https://openalex.org/W2094035326","https://openalex.org/W2094461119","https://openalex.org/W2096391593","https://openalex.org/W2100854157","https://openalex.org/W2104263160","https://openalex.org/W2113131123","https://openalex.org/W2121973264","https://openalex.org/W2124298970","https://openalex.org/W2130563197","https://openalex.org/W2137400100","https://openalex.org/W2141998673","https://openalex.org/W2142352693","https://openalex.org/W2147299274","https://openalex.org/W2148457072","https://openalex.org/W2153894152","https://openalex.org/W2155041441","https://openalex.org/W2163101527","https://openalex.org/W2167734090","https://openalex.org/W2170116036","https://openalex.org/W2184188583","https://openalex.org/W2275684548","https://openalex.org/W2278884322","https://openalex.org/W2318802957","https://openalex.org/W2321982267","https://openalex.org/W2323437298","https://openalex.org/W2325939864","https://openalex.org/W2326115863","https://openalex.org/W2342662179","https://openalex.org/W2394498270","https://openalex.org/W2402901296","https://openalex.org/W2405539902","https://openalex.org/W2405774341","https://openalex.org/W2406954482","https://openalex.org/W2408592723","https://openalex.org/W2421316443","https://openalex.org/W2472613703","https://openalex.org/W2487271655","https://openalex.org/W2516342150","https://openalex.org/W2527611302","https://openalex.org/W2550397165","https://openalex.org/W2551572271","https://openalex.org/W2577762507","https://openalex.org/W2586878855","https://openalex.org/W2621984810","https://openalex.org/W2696731410","https://openalex.org/W2774389566","https://openalex.org/W2793389773","https://openalex.org/W2913340405","https://openalex.org/W2952746495","https://openalex.org/W2962835968","https://openalex.org/W2963045393","https://openalex.org/W2963828919","https://openalex.org/W2978471304","https://openalex.org/W3097096317","https://openalex.org/W3147539069","https://openalex.org/W4253928870","https://openalex.org/W4396952261","https://openalex.org/W6605769872","https://openalex.org/W6633652116","https://openalex.org/W6634154461","https://openalex.org/W6637373629","https://openalex.org/W6686207219","https://openalex.org/W6694617781","https://openalex.org/W6711896204","https://openalex.org/W6713117669","https://openalex.org/W6713510121","https://openalex.org/W6713658392","https://openalex.org/W6713796627","https://openalex.org/W6717465090","https://openalex.org/W6744688305"],"related_works":["https://openalex.org/W3159882232","https://openalex.org/W4241650944","https://openalex.org/W4243125559","https://openalex.org/W4241778367","https://openalex.org/W2752054555","https://openalex.org/W2527828870","https://openalex.org/W2184127972","https://openalex.org/W4238262908","https://openalex.org/W4214489098","https://openalex.org/W46679383"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1],"(SE)":[2],"aims":[3],"to":[4,112],"reduce":[5],"noise":[6],"in":[7,41,93,133,210],"speech":[8,115,148],"signals.":[9],"Most":[10],"SE":[11,50,169,174,185,198],"techniques":[12],"focus":[13],"only":[14],"on":[15],"addressing":[16],"audio":[17,54,72,95,206],"information.":[18],"In":[19,187],"this":[20],"paper,":[21],"inspired":[22],"by":[23],"multimodal":[24],"learning,":[25],"which":[26,52,94],"utilizes":[27],"data":[28,98],"from":[29],"different":[30],"modalities,":[31],"and":[32,55,73,96,105,119,137,171,207],"the":[33,77,82,126,156,177,184,189],"recent":[34],"success":[35],"of":[36,179,203],"convolutional":[37],"neural":[38],"networks":[39],"(CNNs)":[40],"SE,":[42],"we":[43],"propose":[44,65],"an":[45,89,134,166,194],"audio-visual":[46,90],"deep":[47],"CNNs":[48],"(AVDCNN)":[49],"model,":[51,199],"incorporates":[53],"visual":[56,74,97,181,197,208],"streams":[57],"into":[58,108,183],"a":[59,66,109,160],"unified":[60],"network":[61,111],"model.":[62],"We":[63,145],"also":[64,192],"multitask":[67],"learning":[68],"framework":[69],"for":[70],"reconstructing":[71],"signals":[75],"at":[76,125],"output":[78,127],"layer.":[79,128],"Precisely":[80],"speaking,":[81],"proposed":[83],"AVDCNN":[84,157,190],"model":[85,130,158,170,191],"is":[86,131],"structured":[87],"as":[88],"encoder-decoder":[91],"network,":[92],"are":[99,139],"first":[100],"processed":[101],"using":[102,149],"individual":[103],"CNNs,":[104],"then":[106],"fused":[107],"joint":[110],"generate":[113],"enhanced":[114,147],"(the":[116,122],"primary":[117],"task)":[118,124],"reconstructed":[120],"images":[121],"secondary":[123],"The":[129],"trained":[132],"endto-end":[135],"manner,":[136],"parameters":[138],"jointly":[140],"learned":[141],"through":[142],"back":[143],"propagation.":[144],"evaluate":[146],"five":[150],"instrumental":[151],"criteria.":[152],"Results":[153],"show":[154],"that":[155],"yields":[159],"notably":[161],"superior":[162],"performance":[163],"compared":[164],"with":[165],"audio-only":[167],"CNN-based":[168],"two":[172],"conventional":[173],"approaches,":[175],"confirming":[176,200],"effectiveness":[178],"integrating":[180],"information":[182,209],"process.":[186],"addition,":[188],"outperforms":[193],"existing":[195],"audio-":[196],"its":[201],"capability":[202],"effectively":[204],"combining":[205],"SE.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":35},{"year":2023,"cited_by_count":39},{"year":2022,"cited_by_count":27},{"year":2021,"cited_by_count":38},{"year":2020,"cited_by_count":46},{"year":2019,"cited_by_count":23},{"year":2018,"cited_by_count":8}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}