{"id":"https://openalex.org/W4210997382","doi":"https://doi.org/10.1109/taslp.2022.3150220","title":"Modeling Unsupervised Empirical Adaptation by DPGMM and DPGMM-RNN Hybrid Model to Extract Perceptual Features for Low-Resource ASR","display_name":"Modeling Unsupervised Empirical Adaptation by DPGMM and DPGMM-RNN Hybrid Model to Extract Perceptual Features for Low-Resource ASR","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4210997382","doi":"https://doi.org/10.1109/taslp.2022.3150220"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3150220","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3150220","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9657755/09709523.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/ielx7/6570655/9657755/09709523.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":true,"raw_author_name":"Bin Wu","raw_affiliation_strings":["Nara Institute of Science and Technology, Ikoma, Japan"],"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/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]},{"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":["Japan Advanced Institute of Science and Technology, Nomi, Japan","RIKEN Center for Advanced Intelligence Project (AIP), Ikoma, Japan","Nara Institute of Science and Technology, Ikoma, Japan"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Nomi, Japan","institution_ids":["https://openalex.org/I177738480"]},{"raw_affiliation_string":"RIKEN Center for Advanced Intelligence Project (AIP), Ikoma, Japan","institution_ids":["https://openalex.org/I4210126580"]},{"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/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"],"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"],"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":4,"corresponding_author_ids":["https://openalex.org/A5101516754"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":0.2978,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.47414943,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"30","issue":null,"first_page":"901","last_page":"916"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994000196456909,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7619115114212036},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.750698447227478},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.6976350545883179},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5848957896232605},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5203204154968262},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5111857056617737},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.49581655859947205},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.49410679936408997},{"id":"https://openalex.org/keywords/speech-perception","display_name":"Speech perception","score":0.4194377660751343},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.336664080619812},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.32753658294677734},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.29819434881210327},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.23660063743591309},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11051228642463684}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7619115114212036},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.750698447227478},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.6976350545883179},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5848957896232605},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5203204154968262},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5111857056617737},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.49581655859947205},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.49410679936408997},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.4194377660751343},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.336664080619812},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.32753658294677734},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.29819434881210327},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.23660063743591309},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11051228642463684},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2022.3150220","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3150220","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9657755/09709523.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:01146:0005782829","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/4378","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":"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":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal article"},{"id":"pmh:oai:library.naist.jp:10061/14682","is_oa":true,"landing_page_url":"http://hdl.handle.net/10061/14682","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.2022.3150220","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3150220","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9657755/09709523.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":[],"awards":[{"id":"https://openalex.org/G1069223013","display_name":null,"funder_award_id":"JSPS KAKENHI","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G2363020693","display_name":null,"funder_award_id":"21H05054","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3459562248","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3670916553","display_name":null,"funder_award_id":"21H05","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4636223006","display_name":null,"funder_award_id":"JSPS KAK","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7236939988","display_name":null,"funder_award_id":"JP21H03467","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7893352204","display_name":null,"funder_award_id":"JP21H05054","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8843746042","display_name":null,"funder_award_id":"JP21H0505","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4210997382.pdf","grobid_xml":"https://content.openalex.org/works/W4210997382.grobid-xml"},"referenced_works_count":81,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W198924044","https://openalex.org/W625960733","https://openalex.org/W1497856780","https://openalex.org/W1608461387","https://openalex.org/W1635512741","https://openalex.org/W1796128977","https://openalex.org/W1902237438","https://openalex.org/W1980006923","https://openalex.org/W1991923060","https://openalex.org/W2007105567","https://openalex.org/W2011238950","https://openalex.org/W2018567671","https://openalex.org/W2019200248","https://openalex.org/W2037662195","https://openalex.org/W2038142680","https://openalex.org/W2040455912","https://openalex.org/W2041018266","https://openalex.org/W2069429561","https://openalex.org/W2070095866","https://openalex.org/W2076493153","https://openalex.org/W2077382402","https://openalex.org/W2082235945","https://openalex.org/W2082396705","https://openalex.org/W2083750191","https://openalex.org/W2090861223","https://openalex.org/W2095458199","https://openalex.org/W2096162685","https://openalex.org/W2099111195","https://openalex.org/W2101509422","https://openalex.org/W2104752510","https://openalex.org/W2143022183","https://openalex.org/W2148154194","https://openalex.org/W2148389554","https://openalex.org/W2151967501","https://openalex.org/W2155505956","https://openalex.org/W2165712214","https://openalex.org/W2169991335","https://openalex.org/W2327501763","https://openalex.org/W2345811097","https://openalex.org/W2347098582","https://openalex.org/W2395899413","https://openalex.org/W2399576818","https://openalex.org/W2404126548","https://openalex.org/W2404799143","https://openalex.org/W2466905317","https://openalex.org/W2526425061","https://openalex.org/W2610261218","https://openalex.org/W2750248772","https://openalex.org/W2759889345","https://openalex.org/W2786608204","https://openalex.org/W2787447541","https://openalex.org/W2804109700","https://openalex.org/W2895297209","https://openalex.org/W2940544976","https://openalex.org/W2943518292","https://openalex.org/W2950414763","https://openalex.org/W2963620343","https://openalex.org/W2972374322","https://openalex.org/W2973026522","https://openalex.org/W2998470023","https://openalex.org/W3009565979","https://openalex.org/W3095361818","https://openalex.org/W3110371022","https://openalex.org/W3143569452","https://openalex.org/W4206040902","https://openalex.org/W4245838404","https://openalex.org/W4251668937","https://openalex.org/W4254499902","https://openalex.org/W4255383621","https://openalex.org/W4300166480","https://openalex.org/W4320013820","https://openalex.org/W6602180557","https://openalex.org/W6631362777","https://openalex.org/W6675022971","https://openalex.org/W6680970901","https://openalex.org/W6683650587","https://openalex.org/W6744702808","https://openalex.org/W6751796006","https://openalex.org/W6808634324","https://openalex.org/W6842558766"],"related_works":["https://openalex.org/W2376415519","https://openalex.org/W2610308580","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870","https://openalex.org/W2144773493","https://openalex.org/W2138847091"],"abstract_inverted_index":{"Speech":[0],"feature":[1],"extraction":[2],"is":[3,39,83],"critical":[4],"for":[5,60],"ASR":[6,154,172,187],"systems.":[7],"Such":[8],"successful":[9],"features":[10,108,114,117,150,163,183],"as":[11,55,167],"MFCC":[12,116],"and":[13,100,136,171],"PLP":[14],"use":[15],"filterbank":[16],"techniques":[17],"to":[18,25,69,71,105,109,145],"model":[19,26,72,104,138],"log-scaled":[20],"speech":[21,31,43,62],"perception":[22,32,37,63,81],"but":[23],"fail":[24],"the":[27,88,93,101,122,126,134,148,157,160,180],"adaptation":[28,76,79],"of":[29,90,159],"human":[30],"by":[33,41,87],"hearing":[34,42],"experiences.":[35],"Infant":[36],"that":[38,53,82,133,147],"adapted":[40],"without":[44],"text":[45],"may":[46],"cause":[47],"permanent":[48],"brain":[49],"state":[50],"modifications":[51],"(engrams)":[52],"serve":[54],"a":[56],"physical":[57],"fundamental":[58],"basis":[59],"lifetime":[61],"formation.":[64],"This":[65],"realization":[66],"motivates":[67],"us":[68],"propose":[70],"such":[73,165],"an":[74],"unsupervised":[75,162],"process,":[77],"where":[78],"denotes":[80],"affected":[84],"or":[85,125],"changed":[86],"history":[89],"experiences,":[91],"with":[92,118,141,179],"Dirichlet":[94],"Process":[95],"Gaussian":[96],"Mixture":[97],"Model":[98],"(DPGMM)":[99],"DPGMM-RNN":[102,127,137],"hybrid":[103,128],"extract":[106],"perceptual":[107],"improve":[110],"ASR.":[111],"Our":[112,130,153],"proposed":[113,149,161],"extend":[115],"posteriorgrams":[119],"extracted":[120],"from":[121,184],"DPGMM":[123,135],"algorithm":[124],"model.":[129],"analysis":[131],"shows":[132],"perplexities":[139],"agree":[140],"infant":[142],"auditory":[143],"perplexity":[144],"support":[146],"are":[151],"perceptual.":[152],"results":[155],"verify":[156],"effectiveness":[158],"in":[164,186],"tasks":[166],"LVCSR":[168],"on":[169,173],"WSJ":[170],"noisy":[174],"low-resource":[175],"telephone":[176],"conversations,":[177],"compared":[178],"supervised":[181],"bottleneck":[182],"Kaldi":[185],"performance.":[188]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}