{"id":"https://openalex.org/W3196777808","doi":"https://doi.org/10.21437/interspeech.2021-2128","title":"Audio-Visual Multi-Talker Speech Recognition in a Cocktail Party","display_name":"Audio-Visual Multi-Talker Speech Recognition in a Cocktail Party","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3196777808","doi":"https://doi.org/10.21437/interspeech.2021-2128","mag":"3196777808"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-2128","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-2128","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":"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/A5101452320","display_name":"Yifei Wu","orcid":"https://orcid.org/0009-0002-8201-6438"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifei Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090224430","display_name":"Chenda Li","orcid":"https://orcid.org/0000-0003-0299-9914"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenda Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051317379","display_name":"Song Yang","orcid":"https://orcid.org/0000-0002-5385-1402"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009659901","display_name":"Zhongqin Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhongqin Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanmin Qian","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":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3021","last_page":"3025"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9987999796867371,"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":0.7389160394668579},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7224818468093872},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.44325608015060425},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.23466670513153076}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7389160394668579},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7224818468093872},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.44325608015060425},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.23466670513153076}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-2128","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-2128","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1991139021","https://openalex.org/W2015394094","https://openalex.org/W2082183045","https://openalex.org/W2102113734","https://openalex.org/W2143612262","https://openalex.org/W2221409856","https://openalex.org/W2327501763","https://openalex.org/W2460742184","https://openalex.org/W2526425061","https://openalex.org/W2788241093","https://openalex.org/W2890244912","https://openalex.org/W2901907199","https://openalex.org/W2962780374","https://openalex.org/W2963477857","https://openalex.org/W2963528589","https://openalex.org/W2963785710","https://openalex.org/W2963843276","https://openalex.org/W2964171275","https://openalex.org/W2995166068","https://openalex.org/W3008762051","https://openalex.org/W3015445830","https://openalex.org/W3015746570","https://openalex.org/W3017474798","https://openalex.org/W3123318516"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
