{"id":"https://openalex.org/W4226177016","doi":"https://doi.org/10.1109/taslp.2022.3171975","title":"Non-Parametric Bayesian Subspace Models for Acoustic Unit Discovery","display_name":"Non-Parametric Bayesian Subspace Models for Acoustic Unit Discovery","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4226177016","doi":"https://doi.org/10.1109/taslp.2022.3171975"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3171975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3171975","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":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.techrxiv.org/articles/preprint/Non-Parametric_Bayesian_Subspace_Models_for_Acoustic_Unit_Discovery/16618135/2/files/34503725.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Lucas Ondel","orcid":"https://orcid.org/0000-0003-4512-0471"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210113150","display_name":"Laboratoire Interdisciplinaire de Physique","ror":"https://ror.org/023n9q531","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I4210113150","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I4387152856","display_name":"Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique","ror":"https://ror.org/00rd81916","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4387152856"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Lucas Ondel","raw_affiliation_strings":["LISN, CNRS, Universite Paris-Saclay, Orsay, France","Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique","Traitement du Langage Parl\u00e9"],"raw_orcid":"https://orcid.org/0000-0003-4512-0471","affiliations":[{"raw_affiliation_string":"LISN, CNRS, Universite Paris-Saclay, Orsay, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4387152856"]},{"raw_affiliation_string":"Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique","institution_ids":["https://openalex.org/I4210113150","https://openalex.org/I4387152856"]},{"raw_affiliation_string":"Traitement du Langage Parl\u00e9","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007614006","display_name":"Bolaji Yusuf","orcid":"https://orcid.org/0000-0001-9852-3456"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Bolaji Yusuf","raw_affiliation_strings":["Brno University of Technology, Faculty of Information Technology, Brno, Czechia"],"raw_orcid":"https://orcid.org/0000-0001-9852-3456","affiliations":[{"raw_affiliation_string":"Brno University of Technology, Faculty of Information Technology, Brno, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lukas Burget","raw_affiliation_strings":["Brno University of Technology, Faculty of Information Technology, Brno, Czechia","Faculty of Information Technology [Brno]"],"raw_orcid":"https://orcid.org/0000-0002-4951-5908","affiliations":[{"raw_affiliation_string":"Brno University of Technology, Faculty of Information Technology, Brno, Czechia","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Faculty of Information Technology [Brno]","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055086464","display_name":"Murat Sara\u00e7lar","orcid":"https://orcid.org/0000-0002-7435-8510"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Murat Saraclar","raw_affiliation_strings":["Bo&#x011F;azi&#x00E7;i University, Istanbul, Turkey","BUSIM Speech Group"],"raw_orcid":"https://orcid.org/0000-0002-7435-8510","affiliations":[{"raw_affiliation_string":"Bo&#x011F;azi&#x00E7;i University, Istanbul, Turkey","institution_ids":[]},{"raw_affiliation_string":"BUSIM Speech Group","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1161,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50334421,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"30","issue":null,"first_page":"1902","last_page":"1917"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.736299991607666,"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":0.736299991607666,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.1467999964952469,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.014499999582767487,"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/subspace-topology","display_name":"Subspace topology","score":0.6749539375305176},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.6008948087692261},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.5357763767242432},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5277928709983826},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4394945502281189},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.4000460207462311},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3437533974647522},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2982611656188965},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2345067858695984}],"concepts":[{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.6749539375305176},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.6008948087692261},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.5357763767242432},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5277928709983826},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4394945502281189},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.4000460207462311},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3437533974647522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2982611656188965},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2345067858695984},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2022.3171975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3171975","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":"doi:10.36227/techrxiv.16618135","is_oa":true,"landing_page_url":"https://doi.org/10.36227/techrxiv.16618135","pdf_url":"https://www.techrxiv.org/articles/preprint/Non-Parametric_Bayesian_Subspace_Models_for_Acoustic_Unit_Discovery/16618135/2/files/34503725.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"TechRxiv","raw_type":"posted-content"},{"id":"pmh:oai:HAL:hal-03467205v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03467205","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech and Language Processing, 2022, 30, pp.1902 - 1917. &#x27E8;10.1109/TASLP.2022.3171975&#x27E9;","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.36227/techrxiv.16618135","is_oa":true,"landing_page_url":"https://doi.org/10.36227/techrxiv.16618135","pdf_url":"https://www.techrxiv.org/articles/preprint/Non-Parametric_Bayesian_Subspace_Models_for_Acoustic_Unit_Discovery/16618135/2/files/34503725.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"TechRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"display_name":"Climate action","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/13"}],"awards":[{"id":"https://openalex.org/G1319050382","display_name":null,"funder_award_id":"19-26934X","funder_id":"https://openalex.org/F4320321006","funder_display_name":"Grantov\u00e1 Agentura \u010cesk\u00e9 Republiky"},{"id":"https://openalex.org/G2244648182","display_name":null,"funder_award_id":"870930","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G6507486857","display_name":null,"funder_award_id":"e-Infrastructure CZ LM2018140","funder_id":"https://openalex.org/F4320321005","funder_display_name":"Ministerstvo \u0160kolstv\u00ed, Ml\u00e1de\u017ee a T\u011blov\u00fdchovy"}],"funders":[{"id":"https://openalex.org/F4320321005","display_name":"Ministerstvo \u0160kolstv\u00ed, Ml\u00e1de\u017ee a T\u011blov\u00fdchovy","ror":"https://ror.org/037n8p820"},{"id":"https://openalex.org/F4320321006","display_name":"Grantov\u00e1 Agentura \u010cesk\u00e9 Republiky","ror":"https://ror.org/01pv73b02"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4226177016.pdf","grobid_xml":"https://content.openalex.org/works/W4226177016.grobid-xml"},"referenced_works_count":74,"referenced_works":["https://openalex.org/W2195354","https://openalex.org/W1494198834","https://openalex.org/W1503207992","https://openalex.org/W1516111018","https://openalex.org/W1990005915","https://openalex.org/W2072169887","https://openalex.org/W2077804127","https://openalex.org/W2084534958","https://openalex.org/W2099111195","https://openalex.org/W2100768664","https://openalex.org/W2107638917","https://openalex.org/W2109176692","https://openalex.org/W2115979064","https://openalex.org/W2125838338","https://openalex.org/W2193413348","https://openalex.org/W2347098582","https://openalex.org/W2399576818","https://openalex.org/W2401271873","https://openalex.org/W2401396251","https://openalex.org/W2408460974","https://openalex.org/W2483390977","https://openalex.org/W2545177271","https://openalex.org/W2572097499","https://openalex.org/W2586754519","https://openalex.org/W2612661529","https://openalex.org/W2750248772","https://openalex.org/W2752796333","https://openalex.org/W2762715843","https://openalex.org/W2786608204","https://openalex.org/W2805607737","https://openalex.org/W2888911345","https://openalex.org/W2927191280","https://openalex.org/W2928408492","https://openalex.org/W2940544976","https://openalex.org/W2962907457","https://openalex.org/W2963620343","https://openalex.org/W2972374322","https://openalex.org/W2979476256","https://openalex.org/W2991557631","https://openalex.org/W3092791109","https://openalex.org/W3093096176","https://openalex.org/W3100202343","https://openalex.org/W3100270690","https://openalex.org/W3112613336","https://openalex.org/W3125709657","https://openalex.org/W3161215977","https://openalex.org/W3198134274","https://openalex.org/W3198429080","https://openalex.org/W3209059054","https://openalex.org/W4212863985","https://openalex.org/W4237840503","https://openalex.org/W4241943628","https://openalex.org/W4394867155","https://openalex.org/W6600087822","https://openalex.org/W6639732818","https://openalex.org/W6640963894","https://openalex.org/W6645634967","https://openalex.org/W6675022971","https://openalex.org/W6676755231","https://openalex.org/W6677308353","https://openalex.org/W6687566353","https://openalex.org/W6697293080","https://openalex.org/W6704752648","https://openalex.org/W6712648922","https://openalex.org/W6712757354","https://openalex.org/W6731521493","https://openalex.org/W6744702808","https://openalex.org/W6769196770","https://openalex.org/W6770596778","https://openalex.org/W6784355959","https://openalex.org/W6804030475","https://openalex.org/W6865393803","https://openalex.org/W6973666849","https://openalex.org/W7048738093"],"related_works":["https://openalex.org/W4171918","https://openalex.org/W17616020","https://openalex.org/W8136493","https://openalex.org/W159256","https://openalex.org/W8333756","https://openalex.org/W3737758","https://openalex.org/W15295932","https://openalex.org/W10734661","https://openalex.org/W10427819","https://openalex.org/W2123434"],"abstract_inverted_index":{"This":[0],"work":[1],"investigates":[2],"subspace":[3,68,90,124],"non-parametric":[4],"models":[5,55,98,125],"for":[6,72,160],"the":[7,22,41,59,66,70,76,93,141,147,150],"task":[8],"of":[9,13,24,48,54,131],"learning":[10],"a":[11,25,29,88],"set":[12],"acoustic":[14,43,115,161],"units":[15,44,116],"from":[16,32],"unlabeled":[17,94],"speech":[18],"recordings.":[19],"We":[20],"constrain":[21],"base-measure":[23],"Dirichlet-Process":[26],"mixture":[27],"with":[28,112],"phonetic":[30,67],"subspace\u2014estimated":[31],"other":[33,127],"source":[34,50],"languages\u2014to":[35],"build":[36],"aneducated":[37],"prior,":[38],"thereby":[39],"forcing":[40],"learned":[42],"to":[45,86,146,157],"resemble":[46],"phones":[47],"known":[49],"languages.":[51],"Two":[52],"types":[53],"are":[56,99,110,155],"proposed:":[57],"(i)":[58],"Subspace":[60],"HMM":[61,78],"(SHMM)":[62],"which":[63,80],"assumes":[64],"that":[65,122,140,152],"is":[69],"same":[71],"every":[73],"language,":[74],"(ii)":[75],"Hierarchical-Subspace":[77],"(H-SHMM)":[79],"relaxes":[81],"this":[82],"assumption":[83],"and":[84,106,108,134],"allows":[85],"have":[87],"language-specific":[89,153],"estimated":[91],"on":[92,101],"target":[95],"data.":[96],"These":[97],"applied":[100],"3":[102],"languages:":[103],"English,":[104],"Yoruba":[105],"Mboshi":[107],"they":[109],"compared":[111],"various":[113],"competitive":[114],"discovery":[117],"baselines.":[118],"Experimental":[119],"results":[120,144],"show":[121],"both":[123],"outperform":[126],"systems":[128],"in":[129],"terms":[130],"clustering":[132],"quality":[133],"segmentation":[135],"accuracy.":[136],"Moreover,":[137],"we":[138],"observe":[139],"H-SHMM":[142],"provides":[143],"superior":[145],"SHMM":[148],"supporting":[149],"idea":[151],"priors":[154,159],"preferable":[156],"language-agnostic":[158],"unit":[162],"discovery.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2022-05-05T00:00:00"}
