{"id":"https://openalex.org/W3110371022","doi":"https://doi.org/10.1109/taslp.2020.3042016","title":"Tackling Perception Bias in Unsupervised Phoneme Discovery Using DPGMM-RNN Hybrid Model and Functional Load","display_name":"Tackling Perception Bias in Unsupervised Phoneme Discovery Using DPGMM-RNN Hybrid Model and Functional Load","publication_year":2020,"publication_date":"2020-12-02","ids":{"openalex":"https://openalex.org/W3110371022","doi":"https://doi.org/10.1109/taslp.2020.3042016","mag":"3110371022"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.3042016","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3042016","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9289074/09276474.pdf","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":"bronze","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/9289074/09276474.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101516754","display_name":"Bin Wu","orcid":"https://orcid.org/0000-0001-7054-4589"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Bin Wu","raw_affiliation_strings":["Nara Institute of Science and Technology, Ikoma, Japan"],"raw_orcid":"https://orcid.org/0000-0001-7054-4589","affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]},{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Nara Institute of Science and Technology, Ikoma, Japan","RIKEN Center for Advanced Intelligence Project (AIP), Ikoma, Japan"],"raw_orcid":"https://orcid.org/0000-0001-5509-8963","affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"RIKEN Center for Advanced Intelligence Project (AIP), Ikoma, Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052176517","display_name":"Jinsong Zhang","orcid":"https://orcid.org/0000-0002-1603-3136"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinsong Zhang","raw_affiliation_strings":["Beijing Language and Culture University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Language and Culture University, Beijing, China","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]},{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["Nara Institute of Science and Technology, Ikoma, Japan","RIKEN Center for Advanced Intelligence Project (AIP), Ikoma, Japan"],"raw_orcid":"https://orcid.org/0000-0001-6956-3803","affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"RIKEN Center for Advanced Intelligence Project (AIP), Ikoma, Japan","institution_ids":["https://openalex.org/I4210126580"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.297,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55589978,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"29","issue":null,"first_page":"348","last_page":"362"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.7978848814964294},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7065037488937378},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7039932012557983},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.680526614189148},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6754736304283142},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5023417472839355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42789486050605774},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3738999366760254},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.22237327694892883},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14023008942604065},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.0655902624130249}],"concepts":[{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.7978848814964294},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7065037488937378},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7039932012557983},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.680526614189148},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6754736304283142},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5023417472839355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42789486050605774},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3738999366760254},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.22237327694892883},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14023008942604065},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0655902624130249},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2020.3042016","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3042016","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9289074/09276474.pdf","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:irdb.nii.ac.jp:01146:0005782710","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/4259","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal article"},{"id":"pmh:oai:library.naist.jp:10061/14206","is_oa":true,"landing_page_url":"http://hdl.handle.net/10061/14206","pdf_url":null,"source":{"id":"https://openalex.org/S4377196843","display_name":"NAIST Digital Library (Nara Institute of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I75917431","host_organization_name":"Nara Institute of Science and Technology","host_organization_lineage":["https://openalex.org/I75917431"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2020.3042016","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3042016","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9289074/09276474.pdf","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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7300000190734863}],"awards":[{"id":"https://openalex.org/G1688345242","display_name":"Next generation speech translation research","funder_award_id":"17H06101","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6616750388","display_name":null,"funder_award_id":"JP17H06101","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3110371022.pdf","grobid_xml":"https://content.openalex.org/works/W3110371022.grobid-xml"},"referenced_works_count":87,"referenced_works":["https://openalex.org/W52412328","https://openalex.org/W91681889","https://openalex.org/W1600008395","https://openalex.org/W1635512741","https://openalex.org/W1796128977","https://openalex.org/W1977531436","https://openalex.org/W1984314602","https://openalex.org/W1994158173","https://openalex.org/W2010548701","https://openalex.org/W2011334394","https://openalex.org/W2015394094","https://openalex.org/W2017339534","https://openalex.org/W2020607164","https://openalex.org/W2038101708","https://openalex.org/W2051512859","https://openalex.org/W2054168569","https://openalex.org/W2054496875","https://openalex.org/W2056133372","https://openalex.org/W2057007397","https://openalex.org/W2068247585","https://openalex.org/W2089381378","https://openalex.org/W2095089846","https://openalex.org/W2100163972","https://openalex.org/W2100768664","https://openalex.org/W2101234009","https://openalex.org/W2114347655","https://openalex.org/W2117041980","https://openalex.org/W2117126688","https://openalex.org/W2128032727","https://openalex.org/W2138615112","https://openalex.org/W2151967501","https://openalex.org/W2170659185","https://openalex.org/W2252172689","https://openalex.org/W2345811097","https://openalex.org/W2347098582","https://openalex.org/W2395899413","https://openalex.org/W2396043527","https://openalex.org/W2396733358","https://openalex.org/W2399576818","https://openalex.org/W2402366697","https://openalex.org/W2403015869","https://openalex.org/W2404799143","https://openalex.org/W2506406911","https://openalex.org/W2509930204","https://openalex.org/W2579555219","https://openalex.org/W2586754519","https://openalex.org/W2593779438","https://openalex.org/W2750248772","https://openalex.org/W2752796333","https://openalex.org/W2758785877","https://openalex.org/W2759889345","https://openalex.org/W2786608204","https://openalex.org/W2787447541","https://openalex.org/W2796346319","https://openalex.org/W2826003142","https://openalex.org/W2895297209","https://openalex.org/W2940544976","https://openalex.org/W2950414763","https://openalex.org/W2963618559","https://openalex.org/W2963620343","https://openalex.org/W2963799213","https://openalex.org/W2963830550","https://openalex.org/W2972374322","https://openalex.org/W2973026522","https://openalex.org/W3145269374","https://openalex.org/W4246695671","https://openalex.org/W4254499902","https://openalex.org/W6602180557","https://openalex.org/W6638159135","https://openalex.org/W6674922813","https://openalex.org/W6675022971","https://openalex.org/W6675354045","https://openalex.org/W6677461952","https://openalex.org/W6678947187","https://openalex.org/W6680970901","https://openalex.org/W6682569104","https://openalex.org/W6711866534","https://openalex.org/W6712202099","https://openalex.org/W6712444837","https://openalex.org/W6712553779","https://openalex.org/W6713016582","https://openalex.org/W6713256719","https://openalex.org/W6713593416","https://openalex.org/W6734901337","https://openalex.org/W6745117592","https://openalex.org/W6824062597","https://openalex.org/W6973666849"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2382615723","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2623658258","https://openalex.org/W2143413548","https://openalex.org/W1969219540","https://openalex.org/W2370459448","https://openalex.org/W2578422401"],"abstract_inverted_index":{"The":[0,10,98],"human":[1],"perception":[2],"of":[3,12],"phonemes":[4,16,30,76],"is":[5,57],"biased":[6],"against":[7],"speech":[8],"sounds.":[9],"lack":[11],"correspondence":[13],"between":[14,66],"perceptual":[15],"and":[17,94,109],"acoustic":[18],"signals":[19],"forms":[20],"a":[21,104],"big":[22],"challenge":[23],"in":[24],"designing":[25],"unsupervised":[26],"algorithms":[27],"to":[28,64],"distinguish":[29],"from":[31],"sound.":[32],"We":[33,48],"propose":[34],"the":[35,45,58,86,91],"DPGMM-RNN":[36,87],"hybrid":[37,88],"model":[38,89],"that":[39,85],"improves":[40,95],"phoneme":[41,96,111],"categorization":[42],"by":[43,61],"relieving":[44],"fragmentation":[46,92],"problem.":[47],"also":[49],"merge":[50,102],"segments":[51,74],"with":[52],"low":[53],"functional":[54,100],"load,":[55],"which":[56],"work":[59],"done":[60],"segment":[62,105],"contrasts":[63],"differentiate":[65],"utterances,":[67],"just":[68],"like":[69],"humans":[70],"who":[71],"convert":[72],"unambiguous":[73],"into":[75],"as":[77],"units":[78],"for":[79],"immediate":[80],"perception.":[81],"Our":[82],"results":[83],"show":[84],"relieves":[90],"problem":[93],"discriminability.":[97,112],"minimal":[99],"load":[101],"compresses":[103],"system,":[106],"preserves":[107],"information":[108],"keeps":[110]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}