{"id":"https://openalex.org/W3143569452","doi":"https://doi.org/10.1109/slt48900.2021.9383597","title":"Incorporating Discriminative DPGMM Posteriorgrams for Low-Resource ASR","display_name":"Incorporating Discriminative DPGMM Posteriorgrams for Low-Resource ASR","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3143569452","doi":"https://doi.org/10.1109/slt48900.2021.9383597","mag":"3143569452"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383597","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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/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, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, 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, Japan","RIKEN, Center for Advanced Intelligence Project AIP, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project AIP, Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"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, Japan","RIKEN, Center for Advanced Intelligence Project AIP, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project AIP, Japan","institution_ids":["https://openalex.org/I4210126580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"93","issue":null,"first_page":"201","last_page":"208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9941999912261963,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9921000003814697,"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":0.7930843830108643},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7873367071151733},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7063024044036865},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6514068245887756},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6370106935501099},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.537719190120697},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5321490168571472},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4426419138908386},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1903102993965149},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.12537062168121338}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7930843830108643},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7873367071151733},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7063024044036865},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6514068245887756},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6370106935501099},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.537719190120697},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5321490168571472},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4426419138908386},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1903102993965149},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.12537062168121338},{"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/slt48900.2021.9383597","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.550000011920929,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W193119429","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1560013842","https://openalex.org/W1635512741","https://openalex.org/W1796128977","https://openalex.org/W1815076433","https://openalex.org/W1902237438","https://openalex.org/W2020607164","https://openalex.org/W2024490156","https://openalex.org/W2090861223","https://openalex.org/W2100768664","https://openalex.org/W2103387126","https://openalex.org/W2148154194","https://openalex.org/W2151967501","https://openalex.org/W2156983866","https://openalex.org/W2165712214","https://openalex.org/W2183341477","https://openalex.org/W2327501763","https://openalex.org/W2345811097","https://openalex.org/W2347098582","https://openalex.org/W2395899413","https://openalex.org/W2396043527","https://openalex.org/W2399576818","https://openalex.org/W2404799143","https://openalex.org/W2525778437","https://openalex.org/W2526425061","https://openalex.org/W2587741066","https://openalex.org/W2750248772","https://openalex.org/W2759889345","https://openalex.org/W2786608204","https://openalex.org/W2787447541","https://openalex.org/W2940544976","https://openalex.org/W2950414763","https://openalex.org/W2963347649","https://openalex.org/W2963620343","https://openalex.org/W2964121744","https://openalex.org/W2972374322","https://openalex.org/W2973026522","https://openalex.org/W3009565979","https://openalex.org/W3015213852","https://openalex.org/W3102516861","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6633431331","https://openalex.org/W6638159135","https://openalex.org/W6638545294","https://openalex.org/W6675022971","https://openalex.org/W6682569104","https://openalex.org/W6712202099","https://openalex.org/W6712444837","https://openalex.org/W6712553779","https://openalex.org/W6713256719","https://openalex.org/W6726320248","https://openalex.org/W6824062597","https://openalex.org/W6973666849"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W1482209366","https://openalex.org/W2110523656","https://openalex.org/W2521627374","https://openalex.org/W2981954115"],"abstract_inverted_index":{"The":[0,14,41],"first":[1],"step":[2],"in":[3,49,60],"building":[4],"an":[5],"ASR":[6,19,95,181],"system":[7],"is":[8],"to":[9,31,53,86,93,109,124],"extract":[10],"proper":[11],"speech":[12,16,128,151],"features.":[13],"ideal":[15],"features":[17,45,92],"for":[18,188],"must":[20],"also":[21],"have":[22,46,120],"high":[23],"discriminabilities":[24,42],"between":[25,79],"linguistic":[26,55,160],"units":[27,56,161],"and":[28,70,116,183],"be":[29],"robust":[30],"such":[32,110,157],"non-linguistic":[33],"factors":[34],"as":[35,112],"gender,":[36],"age,":[37],"emotions,":[38],"or":[39],"noise.":[40],"of":[43,64,75,90,100,139,148,162],"various":[44],"been":[47,122],"compared":[48],"several":[50,72],"Zerospeech":[51],"challenges":[52],"discover":[54],"without":[57],"any":[58],"transcriptions,":[59],"which":[61,105],"the":[62,88,98,137,149,154,159,173],"posteriorgrams":[63,85],"DPGMM":[65,84,103,132],"clustering":[66,133],"show":[67,176],"strong":[68],"discriminability":[69,89],"get":[71],"top":[73],"results":[74,171],"ABX":[76],"discrimination":[77],"scores":[78],"phonemes.":[80],"This":[81],"paper":[82],"appends":[83],"increase":[87],"acoustic":[91],"enhance":[94],"systems.":[96],"To":[97],"best":[99],"our":[101,177],"knowledge,":[102],"features,":[104],"are":[106,166],"usually":[107],"applied":[108,123],"tasks":[111],"spoken":[113],"term":[114],"detection":[115],"zero":[117],"resources":[118],"tasks,":[119],"not":[121],"large":[125],"vocabulary":[126],"continuous":[127],"recognition":[129],"(LVCSR)":[130],"before.":[131],"can":[134],"dynamically":[135],"change":[136],"number":[138],"Gaussians":[140],"until":[141],"each":[142],"one":[143,145],"fits":[144],"segmental":[146,164],"pattern":[147],"whole":[150],"corpus":[152],"with":[153,191],"highest":[155],"probability":[156],"that":[158],"different":[163],"patterns":[165],"clearly":[167],"discriminated.":[168],"Our":[169],"experimental":[170],"on":[172],"WSJ":[174],"corpora":[175],"proposal":[178],"stably":[179],"improves":[180],"systems":[182],"provides":[184],"even":[185],"more":[186],"improvement":[187],"smaller":[189],"datasets":[190],"fewer":[192],"resources.":[193]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}