{"id":"https://openalex.org/W2963846200","doi":"https://doi.org/10.1109/icassp.2018.8461605","title":"Jointly Tracking and Separating Speech Sources Using Multiple Features and the Generalized Labeled Multi-Bernoulli Framework","display_name":"Jointly Tracking and Separating Speech Sources Using Multiple Features and the Generalized Labeled Multi-Bernoulli Framework","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2963846200","doi":"https://doi.org/10.1109/icassp.2018.8461605","mag":"2963846200"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5083582801","display_name":"Shoufeng Lin","orcid":"https://orcid.org/0000-0002-9508-0706"},"institutions":[{"id":"https://openalex.org/I205640436","display_name":"Curtin University","ror":"https://ror.org/02n415q13","country_code":"AU","type":"education","lineage":["https://openalex.org/I205640436"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Shoufeng Lin","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Curtin University Kent Street, Bentley, Perth, Western Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Curtin University Kent Street, Bentley, Perth, Western Australia","institution_ids":["https://openalex.org/I205640436"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5083582801"],"corresponding_institution_ids":["https://openalex.org/I205640436"],"apc_list":null,"apc_paid":null,"fwci":0.902,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.76580736,"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":"3211","last_page":"3215"},"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/T11309","display_name":"Music and Audio Processing","score":0.9965000152587891,"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":0.9945999979972839,"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":0.7200260162353516},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6903079748153687},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.6436049342155457},{"id":"https://openalex.org/keywords/bernoullis-principle","display_name":"Bernoulli's principle","score":0.6292730569839478},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.6105727553367615},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6016532182693481},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.574374258518219},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5665476322174072},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4665182828903198},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4366014003753662},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4296644628047943},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.42667174339294434},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4141644537448883},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2191450297832489},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09745362401008606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7200260162353516},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6903079748153687},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.6436049342155457},{"id":"https://openalex.org/C152361515","wikidata":"https://www.wikidata.org/wiki/Q181328","display_name":"Bernoulli's principle","level":2,"score":0.6292730569839478},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6105727553367615},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6016532182693481},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.574374258518219},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5665476322174072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4665182828903198},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4366014003753662},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4296644628047943},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.42667174339294434},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4141644537448883},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2191450297832489},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09745362401008606},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":25,"referenced_works":["https://openalex.org/W1557595030","https://openalex.org/W1648602279","https://openalex.org/W1909771825","https://openalex.org/W1987906574","https://openalex.org/W1990449877","https://openalex.org/W2046317813","https://openalex.org/W2049244691","https://openalex.org/W2096855653","https://openalex.org/W2105921478","https://openalex.org/W2106873007","https://openalex.org/W2107493093","https://openalex.org/W2125872840","https://openalex.org/W2130780554","https://openalex.org/W2149900846","https://openalex.org/W2150704472","https://openalex.org/W2154353836","https://openalex.org/W2170768669","https://openalex.org/W2172059073","https://openalex.org/W2328151902","https://openalex.org/W2574583772","https://openalex.org/W3143000476","https://openalex.org/W4256245490","https://openalex.org/W6633511732","https://openalex.org/W6636810956","https://openalex.org/W6682279650"],"related_works":["https://openalex.org/W2353179089","https://openalex.org/W2923538289","https://openalex.org/W2353125546","https://openalex.org/W2470643824","https://openalex.org/W2349635380","https://openalex.org/W2353819554","https://openalex.org/W2359488321","https://openalex.org/W2389866386","https://openalex.org/W4353089801","https://openalex.org/W2131379912"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3],"novel":[4],"joint":[5],"multi-speaker":[6,26],"tracking-and-separation":[7],"method":[8,97],"based":[9],"on":[10],"the":[11,49,62,87,95],"generalized":[12],"labeled":[13],"multi-Bernoulli":[14],"(GLMB)":[15],"multi-target":[16,63],"tracking":[17,27,46],"filter,":[18],"using":[19],"sound":[20],"mixtures":[21],"recorded":[22],"by":[23],"microphones.":[24],"Standard":[25],"algorithms":[28],"usually":[29],"only":[30],"track":[31,100],"speaker":[32,55],"locations,":[33],"and":[34,59,73,80,85,105],"ambiguity":[35,89],"occurs":[36],"when":[37],"speakers":[38,104],"are":[39],"spatially":[40],"close.":[41],"The":[42],"proposed":[43,96],"multi-feature":[44,64,83],"GLMB":[45],"filter":[47],"treats":[48],"set":[50],"of":[51,53,102],"vectors":[52],"associated":[54],"features":[56,68],"(location,":[57],"pitch":[58],"sound)":[60],"as":[61],"observation,":[65],"characterizes":[66],"transitioning":[67],"with":[69],"corresponding":[70],"transition":[71],"models":[72],"overall":[74],"likelihood":[75],"function,":[76],"thus":[77],"jointly":[78],"tracks":[79],"separates":[81],"each":[82],"speaker,":[84],"addresses":[86],"spatial":[88],"problem.":[90],"Numerical":[91],"evaluation":[92],"verifies":[93],"that":[94],"can":[98],"correctly":[99],"locations":[101],"multiple":[103],"meanwhile":[106],"separate":[107],"speech":[108],"signals.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}