{"id":"https://openalex.org/W4281285826","doi":"https://doi.org/10.1145/3517077.3517091","title":"A preliminary study of challenges in extracting purity videos from the AV Speech Benchmark","display_name":"A preliminary study of challenges in extracting purity videos from the AV Speech Benchmark","publication_year":2022,"publication_date":"2022-01-14","ids":{"openalex":"https://openalex.org/W4281285826","doi":"https://doi.org/10.1145/3517077.3517091"},"language":"en","primary_location":{"id":"doi:10.1145/3517077.3517091","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3517077.3517091","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 7th International Conference on Multimedia and Image Processing","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/A5017928207","display_name":"Haoran Yan","orcid":"https://orcid.org/0000-0001-9087-4868"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoran Yan","raw_affiliation_strings":["China Mobile (Suzhou) Software Technology Co. Ltd, China"],"affiliations":[{"raw_affiliation_string":"China Mobile (Suzhou) Software Technology Co. Ltd, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041832225","display_name":"Huijun Lu","orcid":"https://orcid.org/0000-0003-4532-4466"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huijun Lu","raw_affiliation_strings":["China Mobile (Suzhou) Software Technology Co. Ltd, China"],"affiliations":[{"raw_affiliation_string":"China Mobile (Suzhou) Software Technology Co. Ltd, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110716516","display_name":"Dunbo Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dunbo Cai","raw_affiliation_strings":["China Mobile (Suzhou) Software Technology Co. Ltd, China"],"affiliations":[{"raw_affiliation_string":"China Mobile (Suzhou) Software Technology Co. Ltd, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055361187","display_name":"Hang Tao","orcid":"https://orcid.org/0009-0007-1285-968X"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Hang","raw_affiliation_strings":["China Mobile (Suzhou) Software Technology Co. Ltd, China"],"affiliations":[{"raw_affiliation_string":"China Mobile (Suzhou) Software Technology Co. Ltd, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103211253","display_name":"Ling Qian","orcid":"https://orcid.org/0000-0001-5661-1722"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ling Qian","raw_affiliation_strings":["China Mobile (Suzhou) Software Technology Co. Ltd, China"],"affiliations":[{"raw_affiliation_string":"China Mobile (Suzhou) Software Technology Co. Ltd, China","institution_ids":["https://openalex.org/I180662265"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5017928207"],"corresponding_institution_ids":["https://openalex.org/I180662265"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04525535,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"86","last_page":"92"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9850999712944031,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9761999845504761,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7962174415588379},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7786984443664551},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5631740689277649},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5492619276046753},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5080199241638184},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.47585198283195496},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.42003169655799866},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3339572548866272},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07850414514541626}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7962174415588379},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7786984443664551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5631740689277649},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5492619276046753},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5080199241638184},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.47585198283195496},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.42003169655799866},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3339572548866272},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07850414514541626},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3517077.3517091","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3517077.3517091","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 7th International Conference on Multimedia and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2794289187","https://openalex.org/W2962865004","https://openalex.org/W2962960500","https://openalex.org/W6601667473"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175"],"abstract_inverted_index":{"Recently":[0],"reported":[1],"deep":[2,47],"audiovisual":[3],"models":[4,49],"have":[5],"shown":[6],"promising":[7],"results":[8],"on":[9],"solving":[10],"the":[11,32,42,68,80],"cocktail":[12],"party":[13],"problem":[14],"and":[15],"are":[16,22],"attracting":[17],"new":[18],"studies.":[19,28],"Audiovisual":[20],"datasets":[21],"an":[23],"important":[24],"basis":[25],"for":[26,45,50],"these":[27],"Here":[29],"we":[30],"investigate":[31],"AVSpeech":[33],"dataset[1],":[34],"a":[35,59,84,87],"popular":[36],"dataset":[37],"that":[38],"was":[39],"launched":[40],"by":[41],"Google":[43],"team,":[44],"training":[46],"audio-visual":[48],"multi-talker":[51],"speech":[52],"separation.":[53],"Our":[54],"goal":[55],"is":[56],"to":[57],"derive":[58],"special":[60],"kind":[61],"of":[62,72,79],"video,":[63,66],"called":[64],"purity":[65,73],"from":[67],"dataset.":[69],"A":[70],"piece":[71],"video":[74],"contains":[75],"continuous":[76],"image":[77],"frames":[78],"same":[81],"person":[82],"with":[83],"face":[85],"within":[86],"time.":[88]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
