{"id":"https://openalex.org/W2914461061","doi":"https://doi.org/10.1109/taslp.2019.2898818","title":"Robust Pitch Estimation and Tracking For Speakers Based on Subband Encoding and The Generalized Labeled Multi-Bernoulli Filter","display_name":"Robust Pitch Estimation and Tracking For Speakers Based on Subband Encoding and The Generalized Labeled Multi-Bernoulli Filter","publication_year":2019,"publication_date":"2019-02-11","ids":{"openalex":"https://openalex.org/W2914461061","doi":"https://doi.org/10.1109/taslp.2019.2898818","mag":"2914461061"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2898818","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2898818","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2604.01541","any_repository_has_fulltext":true},"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":["School of Electrical Engineering, Computing and Mathematical Sciences, Curtin University, Bentley, WA, Australia"],"raw_orcid":"https://orcid.org/0000-0002-9508-0706","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Computing and Mathematical Sciences, Curtin University, Bentley, WA, 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":0.7725,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.71496162,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"27","issue":"4","first_page":"827","last_page":"841"},"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":0.9991999864578247,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.7052137851715088},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6209334135055542},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.616047203540802},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5896395444869995},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5394706130027771},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5111342072486877},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.5070509910583496},{"id":"https://openalex.org/keywords/bernoullis-principle","display_name":"Bernoulli's principle","score":0.5033466219902039},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.49142134189605713},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.4567609131336212},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3522331118583679},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3284716010093689},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.31962141394615173},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.13554272055625916},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10898402333259583},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10443046689033508}],"concepts":[{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.7052137851715088},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6209334135055542},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.616047203540802},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5896395444869995},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5394706130027771},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5111342072486877},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5070509910583496},{"id":"https://openalex.org/C152361515","wikidata":"https://www.wikidata.org/wiki/Q181328","display_name":"Bernoulli's principle","level":2,"score":0.5033466219902039},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.49142134189605713},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.4567609131336212},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3522331118583679},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3284716010093689},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31962141394615173},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.13554272055625916},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10898402333259583},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10443046689033508},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2019.2898818","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2898818","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2604.01541","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2604.01541","pdf_url":"https://arxiv.org/pdf/2604.01541","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2604.01541","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2604.01541","pdf_url":"https://arxiv.org/pdf/2604.01541","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2914461061.pdf","grobid_xml":"https://content.openalex.org/works/W2914461061.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W23669922","https://openalex.org/W34992941","https://openalex.org/W1493163583","https://openalex.org/W1886421314","https://openalex.org/W1909771825","https://openalex.org/W1946152311","https://openalex.org/W1974387177","https://openalex.org/W1980988001","https://openalex.org/W1984357105","https://openalex.org/W1987906574","https://openalex.org/W1990449877","https://openalex.org/W2043694038","https://openalex.org/W2049244691","https://openalex.org/W2049686551","https://openalex.org/W2050758723","https://openalex.org/W2052252043","https://openalex.org/W2083145261","https://openalex.org/W2091425152","https://openalex.org/W2096506203","https://openalex.org/W2100989275","https://openalex.org/W2101407571","https://openalex.org/W2114537326","https://openalex.org/W2119599673","https://openalex.org/W2131010183","https://openalex.org/W2134025364","https://openalex.org/W2135431242","https://openalex.org/W2135934764","https://openalex.org/W2141684970","https://openalex.org/W2143341575","https://openalex.org/W2149095746","https://openalex.org/W2151251521","https://openalex.org/W2154353836","https://openalex.org/W2171321863","https://openalex.org/W2404934284","https://openalex.org/W2514009036","https://openalex.org/W2561557072","https://openalex.org/W2574583772","https://openalex.org/W2583110984","https://openalex.org/W2588301167","https://openalex.org/W2623227562","https://openalex.org/W2871284238","https://openalex.org/W2889482935","https://openalex.org/W6600956376","https://openalex.org/W6639375475","https://openalex.org/W6679739227","https://openalex.org/W6680683932","https://openalex.org/W6713634346"],"related_works":["https://openalex.org/W3113091479","https://openalex.org/W941090075","https://openalex.org/W2162899405","https://openalex.org/W2044987316","https://openalex.org/W2237480245","https://openalex.org/W3134374554","https://openalex.org/W2519167559","https://openalex.org/W2075065631","https://openalex.org/W4288358396","https://openalex.org/W4311248832"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,8,45,102,115,169],"new":[4,133],"pitch":[5,10,84,110,117,136,157],"estimator":[6],"and":[7,56,77,90,101,126],"novel":[9,46,116],"tracker":[11],"for":[12,83,109,131],"speakers.":[13],"We":[14],"first":[15],"decompose":[16],"the":[17,36,52,57,61,71,78,92,95,123,127,146,175],"sound":[18],"signal":[19],"into":[20],"subbands":[21,39,55],"using":[22,165],"an":[23],"auditory":[24,73],"filterbank,":[25],"assuming":[26],"time-frequency":[27],"sparsity":[28],"of":[29,33,38,54,60,135],"human":[30],"speech.":[31],"Instead":[32],"directly":[34],"selecting":[35],"number":[37,53],"according":[40],"to":[41,50],"experience,":[42],"we":[43,113],"propose":[44],"frequency":[47],"coverage":[48],"metric":[49],"derive":[51],"center":[58],"frequencies":[59],"filterbank.":[62],"The":[63],"subband":[64],"signals":[65],"are":[66,81],"then":[67],"encoded":[68],"inspired":[69],"by":[70],"computational":[72],"scene":[74],"analysis":[75],"approach,":[76],"normalized":[79],"autocorrelations":[80],"calculated":[82],"estimation.":[85],"To":[86],"suppress":[87],"spurious":[88],"errors":[89],"track":[91],"speaker":[93],"identity,":[94],"temporal":[96],"continuity":[97],"constraint":[98],"is":[99,107,178],"exploited":[100],"generalized":[103],"labeled":[104],"multi-Bernoulli":[105],"filter":[106],"adapted":[108],"tracking,":[111],"where":[112],"use":[114],"state":[118],"transition":[119],"model":[120,130],"based":[121],"on":[122],"Ornstein-Uhlenbeck":[124],"process,":[125],"measurement-driven":[128],"birth":[129],"adaptive":[132],"births":[134],"targets.":[137],"Experimental":[138],"evaluations":[139],"with":[140,154],"various":[141],"additive":[142],"noises":[143],"demonstrate":[144],"that":[145,174],"proposed":[147,176],"methods":[148,159],"have":[149],"achieved":[150],"better":[151],"accuracy":[152],"compared":[153],"several":[155],"state-of-the-art":[156],"estimation":[158],"in":[160,168],"most":[161],"studied":[162],"scenarios.":[163],"Tests":[164],"real":[166],"recordings":[167],"reverberant":[170],"room":[171],"also":[172],"show":[173],"method":[177],"robust":[179],"against":[180],"reverberation.":[181]},"counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}
