{"id":"https://openalex.org/W4385822320","doi":"https://doi.org/10.21437/interspeech.2023-574","title":"Target Active Speaker Detection with Audio-visual Cues","display_name":"Target Active Speaker Detection with Audio-visual Cues","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822320","doi":"https://doi.org/10.21437/interspeech.2023-574"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-574","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-574","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/A5016187230","display_name":"Yidi Jiang","orcid":"https://orcid.org/0000-0001-9013-0869"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yidi Jiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026034735","display_name":"Ruijie Tao","orcid":"https://orcid.org/0000-0003-0021-5661"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruijie Tao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060530570","display_name":"Zexu Pan","orcid":"https://orcid.org/0000-0002-8106-1176"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zexu Pan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5016187230"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.0726,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.95084304,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3152","last_page":"3156"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9976999759674072,"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":0.9976999759674072,"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":0.9492999911308289,"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":0.7798341512680054},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6235711574554443},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.598350465297699},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4399590492248535},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36638182401657104},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1339026689529419}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7798341512680054},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6235711574554443},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.598350465297699},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4399590492248535},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36638182401657104},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1339026689529419}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-574","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-574","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/W1891287906","https://openalex.org/W2036807459","https://openalex.org/W2775347418","https://openalex.org/W1969923398","https://openalex.org/W2772917594","https://openalex.org/W2166024367","https://openalex.org/W2755342338","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2058170566"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":10}],"updated_date":"2026-03-05T09:29:38.588285","created_date":"2025-10-10T00:00:00"}
