{"id":"https://openalex.org/W4385822729","doi":"https://doi.org/10.21437/interspeech.2023-2279","title":"MuAViC: A Multilingual Audio-Visual Corpus for Robust Speech Recognition and Robust Speech-to-Text Translation","display_name":"MuAViC: A Multilingual Audio-Visual Corpus for Robust Speech Recognition and Robust Speech-to-Text Translation","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822729","doi":"https://doi.org/10.21437/interspeech.2023-2279"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-2279","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-2279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5101595758","display_name":"Mohamed Anwar","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mohamed Anwar","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100672423","display_name":"Bowen Shi","orcid":"https://orcid.org/0000-0002-0689-9964"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bowen Shi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035752789","display_name":"Vedanuj Goswami","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vedanuj Goswami","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051950818","display_name":"Wei-Ning Hsu","orcid":"https://orcid.org/0000-0001-5546-5217"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei-Ning Hsu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058915697","display_name":"Juan Pino","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juan Pino","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5087491225","display_name":"Changhan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changhan Wang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101595758"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.8594,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.96121955,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4064","last_page":"4068"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9366999864578247,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9366999864578247,"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/computer-science","display_name":"Computer science","score":0.8047319650650024},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7770863175392151},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.6405500173568726},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5626972913742065},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.520571768283844},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5010321140289307},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49684765934944153},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.47843578457832336},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.46594393253326416},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4472445547580719},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4268219769001007},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4148567318916321},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.0862688422203064}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8047319650650024},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7770863175392151},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.6405500173568726},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5626972913742065},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.520571768283844},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5010321140289307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49684765934944153},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.47843578457832336},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.46594393253326416},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4472445547580719},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4268219769001007},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4148567318916321},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0862688422203064},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-2279","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-2279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2197509488","https://openalex.org/W2154135679","https://openalex.org/W2178499706","https://openalex.org/W2024407979","https://openalex.org/W2286739582","https://openalex.org/W2587623425","https://openalex.org/W2133300417","https://openalex.org/W3002002773","https://openalex.org/W3120727700","https://openalex.org/W2794066735"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":3}],"updated_date":"2026-04-04T06:10:10.580331","created_date":"2025-10-10T00:00:00"}
