{"id":"https://openalex.org/W2512544816","doi":"https://doi.org/10.21437/interspeech.2016-412","title":"Open-Domain Audio-Visual Speech Recognition: A Deep Learning Approach","display_name":"Open-Domain Audio-Visual Speech Recognition: A Deep Learning Approach","publication_year":2016,"publication_date":"2016-08-29","ids":{"openalex":"https://openalex.org/W2512544816","doi":"https://doi.org/10.21437/interspeech.2016-412","mag":"2512544816"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2016-412","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-412","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","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/A5003251887","display_name":"Yajie Miao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yajie Miao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4187,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.91038351,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3414","last_page":"3418"},"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":0.9998000264167786,"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":0.9995999932289124,"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":0.8102099299430847},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7357604503631592},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.656169593334198},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5665504932403564},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5246886610984802},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.459696888923645},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41103285551071167},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4006868600845337},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.30792129039764404},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2273682951927185}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8102099299430847},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7357604503631592},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.656169593334198},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5665504932403564},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5246886610984802},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.459696888923645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41103285551071167},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4006868600845337},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.30792129039764404},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2273682951927185},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2016-412","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-412","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","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":26,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W124086577","https://openalex.org/W135040384","https://openalex.org/W567546468","https://openalex.org/W1929897159","https://openalex.org/W1985371235","https://openalex.org/W1992475611","https://openalex.org/W2015633636","https://openalex.org/W2045317385","https://openalex.org/W2079623482","https://openalex.org/W2092572762","https://openalex.org/W2092776130","https://openalex.org/W2108598243","https://openalex.org/W2113786253","https://openalex.org/W2124174353","https://openalex.org/W2147768505","https://openalex.org/W2151096985","https://openalex.org/W2157827878","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2213952365","https://openalex.org/W2293634267","https://openalex.org/W2395655916","https://openalex.org/W2403524927","https://openalex.org/W2406753715","https://openalex.org/W2963211739"],"related_works":["https://openalex.org/W2547431347","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W642007152","https://openalex.org/W2131711534","https://openalex.org/W2184127972","https://openalex.org/W2343205865","https://openalex.org/W2341426843","https://openalex.org/W2009814707"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
