{"id":"https://openalex.org/W4385823040","doi":"https://doi.org/10.21437/interspeech.2023-2256","title":"An Improved End-to-End Audio-Visual Speech Recognition Model","display_name":"An Improved End-to-End Audio-Visual Speech Recognition Model","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823040","doi":"https://doi.org/10.21437/interspeech.2023-2256"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-2256","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-2256","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/A5102000358","display_name":"Sheng Yang","orcid":"https://orcid.org/0000-0002-5884-4893"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sheng Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102784428","display_name":"Zheng Gong","orcid":"https://orcid.org/0000-0002-7430-4889"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng Gong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101068304","display_name":"Jia Kang","orcid":"https://orcid.org/0000-0001-7600-4540"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia Kang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102000358"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2033,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.43462477,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3093","last_page":"3097"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8878999948501587,"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":0.8878999948501587,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.8172467947006226},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7142902612686157},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6505295038223267},{"id":"https://openalex.org/keywords/end-user","display_name":"End user","score":0.44384855031967163},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.43893927335739136},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.241186261177063},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.19076433777809143},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10221567749977112}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8172467947006226},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7142902612686157},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6505295038223267},{"id":"https://openalex.org/C91262260","wikidata":"https://www.wikidata.org/wiki/Q528074","display_name":"End user","level":2,"score":0.44384855031967163},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.43893927335739136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.241186261177063},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.19076433777809143},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10221567749977112}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-2256","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-2256","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2331065455","https://openalex.org/W4299590256","https://openalex.org/W2368779261","https://openalex.org/W2778699561","https://openalex.org/W3196861523","https://openalex.org/W4295833677","https://openalex.org/W4226075960","https://openalex.org/W1547975896","https://openalex.org/W2949002666","https://openalex.org/W4385823040"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}
