{"id":"https://openalex.org/W4385823440","doi":"https://doi.org/10.21437/interspeech.2023-598","title":"Semantic VAD: Low-Latency Voice Activity Detection for Speech Interaction","display_name":"Semantic VAD: Low-Latency Voice Activity Detection for Speech Interaction","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823440","doi":"https://doi.org/10.21437/interspeech.2023-598"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-598","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-598","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/A5069196598","display_name":"Mohan Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mohan Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008475151","display_name":"Yuchun Shu","orcid":"https://orcid.org/0000-0002-4375-1002"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuchun Shu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005792493","display_name":"Lingyun Zuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lingyun Zuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100428456","display_name":"Qian Chen","orcid":"https://orcid.org/0000-0002-1909-302X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101777591","display_name":"Shiliang Zhang","orcid":"https://orcid.org/0000-0002-9524-1602"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiliang Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100436848","display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0003-1124-0854"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li-Rong Dai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5069196598"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1684,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82846858,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5047","last_page":"5051"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9526000022888184,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9526000022888184,"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/T12031","display_name":"Speech and dialogue systems","score":0.9031999707221985,"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":0.7654841542243958},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.7146399021148682},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5815718173980713},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5648046731948853},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.4774777889251709},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.28621113300323486},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.19298985600471497},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11722409725189209}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7654841542243958},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.7146399021148682},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5815718173980713},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5648046731948853},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.4774777889251709},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28621113300323486},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.19298985600471497},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11722409725189209}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-598","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-598","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/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2131711534","https://openalex.org/W2559837139","https://openalex.org/W1151175420","https://openalex.org/W2407342067","https://openalex.org/W2166690696","https://openalex.org/W2541680182"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-15T08:27:34.491423","created_date":"2025-10-10T00:00:00"}
