{"id":"https://openalex.org/W4405632986","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800033","title":"Robust Audio-Visual Speech Enhancement: Correcting Misassignments in Complex Environments With Advanced Post-Processing","display_name":"Robust Audio-Visual Speech Enhancement: Correcting Misassignments in Complex Environments With Advanced Post-Processing","publication_year":2024,"publication_date":"2024-10-17","ids":{"openalex":"https://openalex.org/W4405632986","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800033"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda64382.2024.10800033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","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/A5113382917","display_name":"Wenze Ren","orcid":null},"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":true,"raw_author_name":"Wenze Ren","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064333828","display_name":"Kuo-Hsuan Hung","orcid":"https://orcid.org/0000-0002-6298-5269"},"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":"Kuo-Hsuan Hung","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030791258","display_name":"Rong Chao","orcid":"https://orcid.org/0000-0001-6930-959X"},"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":"Rong Chao","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012212264","display_name":"You-Jin Li","orcid":null},"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":"YouJin Li","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Academia Sinica"],"affiliations":[{"raw_affiliation_string":"Academia Sinica","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Academia Sinica"],"affiliations":[{"raw_affiliation_string":"Academia Sinica","institution_ids":["https://openalex.org/I84653119"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5113382917"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26455261,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.9983000159263611,"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":0.9983000159263611,"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":0.9473999738693237,"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":0.9264000058174133,"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":0.8122895359992981},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5957337021827698},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5777994394302368},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5468929409980774},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5375696420669556},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5311191082000732},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4703260660171509},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.29863178730010986},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2436770796775818},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.156190425157547},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.08145192265510559}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8122895359992981},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5957337021827698},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5777994394302368},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5468929409980774},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5375696420669556},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5311191082000732},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4703260660171509},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.29863178730010986},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2436770796775818},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.156190425157547},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.08145192265510559}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda64382.2024.10800033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2402901296","https://openalex.org/W2405774341","https://openalex.org/W2460742184","https://openalex.org/W2735090526","https://openalex.org/W2788241093","https://openalex.org/W2890952074","https://openalex.org/W2962866211","https://openalex.org/W2964171275","https://openalex.org/W3024869864","https://openalex.org/W3096408984","https://openalex.org/W3163652268","https://openalex.org/W4214567298","https://openalex.org/W4226062543","https://openalex.org/W4319862411","https://openalex.org/W4372259900","https://openalex.org/W4372271367","https://openalex.org/W4392909516","https://openalex.org/W6745136726","https://openalex.org/W6757632829","https://openalex.org/W6783890765","https://openalex.org/W6785269020","https://openalex.org/W6788484017"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W3211091508","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W193702574","https://openalex.org/W72660888","https://openalex.org/W2089240210","https://openalex.org/W2063862874","https://openalex.org/W1546240199"],"abstract_inverted_index":{"This":[0,113],"paper":[1],"addresses":[2],"the":[3,43,49,68,76,88,98,106,116],"prevalent":[4],"issue":[5],"of":[6],"incorrect":[7],"speech":[8,12,45],"output":[9],"in":[10,58,133],"audio-visual":[11],"enhancement":[13],"(AVSE)":[14],"systems,":[15],"which":[16],"is":[17],"often":[18],"caused":[19],"by":[20,109],"poor":[21],"video":[22],"quality":[23],"and":[24,27,84,124],"mismatched":[25],"training":[26,60,95],"test":[28],"data.":[29],"We":[30,52],"introduce":[31],"a":[32,55,110,127],"post-processing":[33],"classifier":[34],"(PPC)":[35],"to":[36,48,61],"rectify":[37],"these":[38],"erroneous":[39],"outputs,":[40],"ensuring":[41],"that":[42,72],"enhanced":[44],"corresponds":[46],"accurately":[47],"intended":[50],"speaker.":[51],"also":[53],"adopt":[54],"mixup":[56],"strategy":[57],"PPC":[59,74,86],"improve":[62,81],"its":[63],"robustness.":[64],"Experimental":[65],"results":[66],"on":[67],"AVSE-challenge":[69],"dataset":[70],"show":[71],"integrating":[73],"into":[75],"AVSE":[77,82,89],"model":[78,90,108],"can":[79],"significantly":[80],"performance,":[83],"combining":[85],"with":[87,92],"trained":[91],"permutation":[93],"invariant":[94],"(PIT)":[96],"yields":[97],"best":[99],"performance.":[100],"The":[101],"proposed":[102],"method":[103],"substantially":[104],"outperforms":[105],"baseline":[107],"large":[111],"margin.":[112],"work":[114],"highlights":[115],"potential":[117],"for":[118,130],"broader":[119],"applications":[120],"across":[121],"various":[122],"modalities":[123],"architectures,":[125],"providing":[126],"promising":[128],"direction":[129],"future":[131],"research":[132],"this":[134],"field.":[135]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}