{"id":"https://openalex.org/W4296069282","doi":"https://doi.org/10.21437/interspeech.2022-10190","title":"Audio Visual Multi-Speaker Tracking with Improved GCF and PMBM Filter","display_name":"Audio Visual Multi-Speaker Tracking with Improved GCF and PMBM Filter","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296069282","doi":"https://doi.org/10.21437/interspeech.2022-10190"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10190","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10190","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5057816329","display_name":"Jinzheng Zhao","orcid":"https://orcid.org/0009-0004-3910-850X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jinzheng Zhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063162390","display_name":"Peipei Wu","orcid":"https://orcid.org/0000-0002-3969-3372"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peipei Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080214850","display_name":"Xubo Liu","orcid":"https://orcid.org/0000-0002-2558-0959"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xubo Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012386816","display_name":"Shidrokh Goudarzi","orcid":"https://orcid.org/0000-0003-0383-3553"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shidrokh Goudarzi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089924305","display_name":"Haohe Liu","orcid":"https://orcid.org/0000-0003-1036-7888"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haohe Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100577133","display_name":"Yong Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"YONG XU","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5057816329"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4909,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.59115324,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3704","last_page":"3708"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9970999956130981,"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":0.9970999956130981,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9710000157356262,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13717","display_name":"Advanced Algorithms and Applications","score":0.9684000015258789,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.773826003074646},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6038969159126282},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5723792314529419},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5685814619064331},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5140382051467896},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.44825124740600586},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4372623562812805},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.42865002155303955},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4268532395362854},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.17317917943000793},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0761546790599823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.773826003074646},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6038969159126282},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5723792314529419},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5685814619064331},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5140382051467896},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.44825124740600586},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4372623562812805},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.42865002155303955},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4268532395362854},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.17317917943000793},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0761546790599823},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10190","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10190","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["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","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2215635302"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
