{"id":"https://openalex.org/W3196861523","doi":"https://doi.org/10.21437/interspeech.2021-1621","title":"End-to-End Audio-Visual Speech Recognition for Overlapping Speech","display_name":"End-to-End Audio-Visual Speech Recognition for Overlapping Speech","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3196861523","doi":"https://doi.org/10.21437/interspeech.2021-1621","mag":"3196861523"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1621","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5077077136","display_name":"Richard C. Rose","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Richard Rose","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005881531","display_name":"Olivier Siohan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Olivier Siohan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101403998","display_name":"Anshuman Tripathi","orcid":"https://orcid.org/0000-0002-4902-3719"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anshuman Tripathi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5048852285","display_name":"Otavio Braga","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Otavio Braga","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5077077136"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3047,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54090602,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3016","last_page":"3020"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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/computer-science","display_name":"Computer science","score":0.7862135171890259},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.784719705581665},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.7613314390182495},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6603997349739075},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5165671110153198},{"id":"https://openalex.org/keywords/speech-analytics","display_name":"Speech analytics","score":0.48666173219680786},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.47233524918556213},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.46375396847724915},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4210958480834961},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.390614777803421},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26957976818084717},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.22228652238845825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7862135171890259},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.784719705581665},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.7613314390182495},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6603997349739075},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5165671110153198},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.48666173219680786},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.47233524918556213},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.46375396847724915},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4210958480834961},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.390614777803421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26957976818084717},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.22228652238845825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-1621","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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":14,"referenced_works":["https://openalex.org/W85853872","https://openalex.org/W2033256038","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2890952074","https://openalex.org/W2963403868","https://openalex.org/W2963785710","https://openalex.org/W3006974783","https://openalex.org/W3015746570","https://openalex.org/W3015834770","https://openalex.org/W3016010032","https://openalex.org/W3016232124","https://openalex.org/W3016400019","https://openalex.org/W3097966334"],"related_works":["https://openalex.org/W2157598242","https://openalex.org/W1911859126","https://openalex.org/W2184127972","https://openalex.org/W2619911963","https://openalex.org/W1583620810","https://openalex.org/W642007152","https://openalex.org/W2131711534","https://openalex.org/W2341426843","https://openalex.org/W2110852049","https://openalex.org/W4387712795"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
