{"id":"https://openalex.org/W4214741385","doi":"https://doi.org/10.1145/3508546.3508638","title":"Audio-visual Speech Enhancement by Using the Correlation Deeply","display_name":"Audio-visual Speech Enhancement by Using the Correlation Deeply","publication_year":2021,"publication_date":"2021-12-22","ids":{"openalex":"https://openalex.org/W4214741385","doi":"https://doi.org/10.1145/3508546.3508638"},"language":"en","primary_location":{"id":"doi:10.1145/3508546.3508638","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3508546.3508638","pdf_url":null,"source":{"id":"https://openalex.org/S4363608505","display_name":"2021 4th International Conference on Algorithms, Computing and Artificial Intelligence","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":"2021 4th International Conference on Algorithms, Computing and Artificial Intelligence","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/A5006555821","display_name":"Xiaolong Wang","orcid":"https://orcid.org/0000-0003-1201-3530"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolong Wang","raw_affiliation_strings":["School of Electrical Engineering and Automation, Anhui University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Automation, Anhui University, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345405","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0002-5600-9202"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["School of Electrical Engineering and Automation, Anhui University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Automation, Anhui University, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100689763","display_name":"Wei Li","orcid":"https://orcid.org/0000-0001-7367-4178"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9941999912261963,"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":0.9890000224113464,"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/audio-visual","display_name":"Audio visual","score":0.5852043628692627},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5710330009460449},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.560113787651062},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.5190297365188599},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.42764344811439514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24133500456809998},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1821838617324829},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08789524435997009},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.0557079017162323}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5852043628692627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5710330009460449},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.560113787651062},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5190297365188599},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.42764344811439514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24133500456809998},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1821838617324829},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08789524435997009},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0557079017162323},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3508546.3508638","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3508546.3508638","pdf_url":null,"source":{"id":"https://openalex.org/S4363608505","display_name":"2021 4th International Conference on Algorithms, Computing and Artificial Intelligence","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":"2021 4th International Conference on Algorithms, Computing and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2962935966","https://openalex.org/W2964171275","https://openalex.org/W3011424113","https://openalex.org/W3020804303","https://openalex.org/W3163287738","https://openalex.org/W3169318522","https://openalex.org/W3175514052","https://openalex.org/W3182657421","https://openalex.org/W4214644094","https://openalex.org/W4214759869","https://openalex.org/W4289665794","https://openalex.org/W4376548714","https://openalex.org/W6774616389"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853"],"abstract_inverted_index":{"Audio-visual":[0],"speech":[1,36,58,65,95],"separation":[2],"aims":[3],"to":[4,63,74],"separate":[5],"distinct":[6],"voice":[7],"from":[8],"an":[9],"audio":[10,43],"mixture":[11],"of":[12,35,88,94],"multiple":[13],"simultaneous":[14],"speakers.":[15],"The":[16,82],"problem":[17],"is":[18],"that":[19,49,85],"visual":[20,53,61],"information":[21,55,62],"can\u2019t":[22],"be":[23],"fully":[24],"utilized.":[25],"We":[26,47,68],"propose":[27,48],"a":[28,70],"network":[29,77],"which":[30],"can":[31,90],"improve":[32,64,91],"the":[33,40,76,79,86,92],"functioning":[34],"enhancement":[37,66,96],"by":[38,56],"using":[39,60],"correlation":[41],"between":[42],"and":[44],"vision":[45],"deeply.":[46],"we":[50],"could":[51],"extract":[52],"feature":[54],"utilizing":[57],"before":[59],"performance.":[67],"make":[69],"continuous":[71],"dataset,":[72],"CRF,":[73],"fit":[75],"at":[78],"same":[80],"time.":[81],"results":[83],"demonstrate":[84],"combination":[87],"them":[89],"performance":[93],"effectively.":[97]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}