{"id":"https://openalex.org/W4385478414","doi":"https://doi.org/10.1109/icasspw59220.2023.10193049","title":"Audio-Visual Speech Enhancement and Separation by Utilizing Multi-Modal Self-Supervised Embeddings","display_name":"Audio-Visual Speech Enhancement and Separation by Utilizing Multi-Modal Self-Supervised Embeddings","publication_year":2023,"publication_date":"2023-06-04","ids":{"openalex":"https://openalex.org/W4385478414","doi":"https://doi.org/10.1109/icasspw59220.2023.10193049"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw59220.2023.10193049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10193049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5074950328","display_name":"I-Chun Chern","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"I-Chun Chern","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"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"]},{"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":"Kuo-Hsuan Hung","raw_affiliation_strings":["National Taiwan University,Taiwan","Academia Sinica, Taiwan","National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I84653119"]},{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348255","display_name":"Yi-Ting Chen","orcid":"https://orcid.org/0000-0001-6748-6832"},"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":"Yi-Ting Chen","raw_affiliation_strings":["Academia Sinica,Taiwan","Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica,Taiwan","institution_ids":["https://openalex.org/I84653119"]},{"raw_affiliation_string":"Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089443958","display_name":"Tassadaq Hussain","orcid":"https://orcid.org/0000-0003-1396-5429"},"institutions":[{"id":"https://openalex.org/I251738","display_name":"Edinburgh Napier University","ror":"https://ror.org/03zjvnn91","country_code":"GB","type":"education","lineage":["https://openalex.org/I251738"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tassadaq Hussain","raw_affiliation_strings":["Edinburgh Napier University,UK","Edinburgh Napier University, UK"],"affiliations":[{"raw_affiliation_string":"Edinburgh Napier University,UK","institution_ids":["https://openalex.org/I251738"]},{"raw_affiliation_string":"Edinburgh Napier University, UK","institution_ids":["https://openalex.org/I251738"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068981769","display_name":"Mandar Gogate","orcid":"https://orcid.org/0000-0003-1712-9014"},"institutions":[{"id":"https://openalex.org/I251738","display_name":"Edinburgh Napier University","ror":"https://ror.org/03zjvnn91","country_code":"GB","type":"education","lineage":["https://openalex.org/I251738"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mandar Gogate","raw_affiliation_strings":["Edinburgh Napier University,UK","Edinburgh Napier University, UK"],"affiliations":[{"raw_affiliation_string":"Edinburgh Napier University,UK","institution_ids":["https://openalex.org/I251738"]},{"raw_affiliation_string":"Edinburgh Napier University, UK","institution_ids":["https://openalex.org/I251738"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062211930","display_name":"Amir Hussain","orcid":"https://orcid.org/0000-0002-8080-082X"},"institutions":[{"id":"https://openalex.org/I251738","display_name":"Edinburgh Napier University","ror":"https://ror.org/03zjvnn91","country_code":"GB","type":"education","lineage":["https://openalex.org/I251738"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Amir Hussain","raw_affiliation_strings":["Edinburgh Napier University,UK","Edinburgh Napier University, UK"],"affiliations":[{"raw_affiliation_string":"Edinburgh Napier University,UK","institution_ids":["https://openalex.org/I251738"]},{"raw_affiliation_string":"Edinburgh Napier University, UK","institution_ids":["https://openalex.org/I251738"]}]},{"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/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,Taiwan","Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica,Taiwan","institution_ids":["https://openalex.org/I84653119"]},{"raw_affiliation_string":"Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058567113","display_name":"Jen-Cheng Hou","orcid":"https://orcid.org/0000-0002-4010-0220"},"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":"Jen-Cheng Hou","raw_affiliation_strings":["Academia Sinica,Taiwan","Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica,Taiwan","institution_ids":["https://openalex.org/I84653119"]},{"raw_affiliation_string":"Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I84653119"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5074950328"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":2.3827,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.89617554,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9975000023841858,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/audio-visual","display_name":"Audio visual","score":0.7867835164070129},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7510466575622559},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7506353855133057},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.6698553562164307},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6290394067764282},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5897274017333984},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5378624200820923},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.47134846448898315},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.350582480430603},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3250104784965515},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32393503189086914},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.12458354234695435},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0718914270401001}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7867835164070129},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7510466575622559},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7506353855133057},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6698553562164307},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6290394067764282},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5897274017333984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5378624200820923},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.47134846448898315},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.350582480430603},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3250104784965515},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32393503189086914},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.12458354234695435},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0718914270401001},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icasspw59220.2023.10193049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10193049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository@napier.ac.uk:3609134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ICASSPW59220.2023.10193049","pdf_url":null,"source":{"id":"https://openalex.org/S4306402591","display_name":"Edinburgh Napier Research Repository (Edinburgh Napier University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I251738","host_organization_name":"Edinburgh Napier University","host_organization_lineage":["https://openalex.org/I251738"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Presentation / Conference Contribution"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2044893557","https://openalex.org/W2101042021","https://openalex.org/W2141998673","https://openalex.org/W2405774341","https://openalex.org/W2788241093","https://openalex.org/W2891205112","https://openalex.org/W2908510526","https://openalex.org/W2962935966","https://openalex.org/W2965390715","https://openalex.org/W2966715458","https://openalex.org/W3033703941","https://openalex.org/W3173382920","https://openalex.org/W3182657421","https://openalex.org/W3197419327","https://openalex.org/W3205715971","https://openalex.org/W3209059054","https://openalex.org/W4214567298","https://openalex.org/W4221153068","https://openalex.org/W4224933800","https://openalex.org/W4226403810","https://openalex.org/W4285250921","https://openalex.org/W4285258106","https://openalex.org/W4297841864","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6754420807","https://openalex.org/W6757817989","https://openalex.org/W6766904570","https://openalex.org/W6810168380"],"related_works":["https://openalex.org/W4386799044","https://openalex.org/W2271369634","https://openalex.org/W2773208253","https://openalex.org/W2350550760","https://openalex.org/W2560646951","https://openalex.org/W2770665941","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853","https://openalex.org/W197907117"],"abstract_inverted_index":{"AV-HuBERT,":[0],"a":[1],"multi-modal":[2,34,50,123],"self-supervised":[3,35,124],"learning":[4],"model,":[5],"has":[6],"been":[7],"shown":[8],"to":[9,47,132],"be":[10,30,45,130],"effective":[11],"for":[12,79,113],"categorical":[13],"problems":[14],"such":[15,42,54],"as":[16,55],"automatic":[17],"speech":[18,27,57,62],"recognition":[19],"and":[20,60,81,97],"lip-reading.":[21],"This":[22],"suggests":[23],"that":[24,87,122],"useful":[25],"audio-visual":[26,56,61,133],"representations":[28,43],"can":[29,44,129],"obtained":[31,126],"via":[32],"utilizing":[33],"embeddings.":[36],"Nevertheless,":[37],"it":[38],"is":[39],"unclear":[40],"if":[41],"generalized":[46,131],"solve":[48],"real-world":[49],"AV":[51],"regression":[52,134],"tasks,":[53],"enhancement":[58],"(AVSE)":[59],"separation":[63],"(AVSS).":[64],"In":[65,102],"this":[66],"study,":[67],"we":[68],"leveraged":[69],"the":[70,94,107,114],"pre-trained":[71],"AV-HuBERT":[72,128],"model":[73,90,112],"followed":[74],"by":[75],"an":[76],"SE":[77,100],"module":[78],"AVSE":[80,96],"AVSS.":[82],"Comparative":[83],"experimental":[84],"results":[85,105],"demonstrate":[86],"our":[88,104,110],"proposed":[89,111],"performs":[91],"better":[92],"than":[93],"state-of-the-art":[95],"traditional":[98],"audio-only":[99],"models.":[101],"summary,":[103],"confirm":[106],"effectiveness":[108],"of":[109],"AVSS":[115],"task":[116],"with":[117],"proper":[118],"fine-tuning":[119],"strategies,":[120],"demonstrating":[121],"embeddings":[125],"from":[127],"tasks.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}
