{"id":"https://openalex.org/W2586754519","doi":"https://doi.org/10.1109/slt.2016.7846245","title":"Iterative training of a DPGMM-HMM acoustic unit recognizer in a zero resource scenario","display_name":"Iterative training of a DPGMM-HMM acoustic unit recognizer in a zero resource scenario","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2586754519","doi":"https://doi.org/10.1109/slt.2016.7846245","mag":"2586754519"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2016.7846245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2016.7846245","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5015873217","display_name":"Michael Heck","orcid":"https://orcid.org/0000-0001-9841-5025"},"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":"Michael Heck","raw_affiliation_strings":["Augmented Human Communication Laboratory, Nara Institute of Science and Technology, Nara, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Augmented Human Communication Laboratory, Nara Institute of Science and Technology, Nara, 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/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":["Augmented Human Communication Laboratory, Nara Institute of Science and Technology, Nara, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Augmented Human Communication Laboratory, Nara Institute of Science and Technology, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"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/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":["Augmented Human Communication Laboratory, Nara Institute of Science and Technology, Nara, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Augmented Human Communication Laboratory, Nara Institute of Science and Technology, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"57","last_page":"63"},"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/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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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/computer-science","display_name":"Computer science","score":0.8200418949127197},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7598502039909363},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.66424560546875},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6554424166679382},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5553756356239319},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5005638599395752},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49985265731811523},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4415552020072937},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4403769075870514},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4173971712589264},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.17192527651786804}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8200418949127197},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7598502039909363},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.66424560546875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6554424166679382},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5553756356239319},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5005638599395752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49985265731811523},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4415552020072937},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4403769075870514},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4173971712589264},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.17192527651786804},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2016.7846245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2016.7846245","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.699999988079071}],"awards":[{"id":"https://openalex.org/G902618119","display_name":"Integration of Event Related Brain Potentials into Speech Recognition Framework","funder_award_id":"26870371","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":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W66167291","https://openalex.org/W1524333225","https://openalex.org/W1631260214","https://openalex.org/W1975113979","https://openalex.org/W2056786202","https://openalex.org/W2064210461","https://openalex.org/W2078769636","https://openalex.org/W2100768664","https://openalex.org/W2113641473","https://openalex.org/W2114347655","https://openalex.org/W2117041980","https://openalex.org/W2118841860","https://openalex.org/W2119187236","https://openalex.org/W2126203737","https://openalex.org/W2128032727","https://openalex.org/W2137826140","https://openalex.org/W2146950091","https://openalex.org/W2345811097","https://openalex.org/W2395899413","https://openalex.org/W2399576818","https://openalex.org/W2401464865","https://openalex.org/W2402014506","https://openalex.org/W2509930204","https://openalex.org/W2786608204","https://openalex.org/W2963620343","https://openalex.org/W2963684067","https://openalex.org/W3148201686","https://openalex.org/W4234482113","https://openalex.org/W6602705600","https://openalex.org/W6631362777","https://openalex.org/W6636811518","https://openalex.org/W6675022971","https://openalex.org/W6677734967","https://openalex.org/W6678947187","https://openalex.org/W6704305767","https://openalex.org/W6712444837","https://openalex.org/W6712553779","https://openalex.org/W6973666849"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2160650576","https://openalex.org/W2121652828","https://openalex.org/W2735380212"],"abstract_inverted_index":{"In":[0],"this":[1,110],"paper":[2],"we":[3,26],"propose":[4],"a":[5,9,15,39,56,71],"framework":[6,37],"for":[7,42,58],"building":[8],"full-fledged":[10],"acoustic":[11,45,76,112],"unit":[12,113],"recognizer":[13,114],"in":[14],"zero":[16],"resource":[17],"setting,":[18],"i.e.,":[19],"without":[20],"any":[21],"provided":[22],"labels.":[23],"For":[24],"that,":[25],"combine":[27],"an":[28,119],"iterative":[29,59,105],"Dirichlet":[30],"process":[31],"Gaussian":[32],"mixture":[33],"model":[34,46,51,60,107],"(DPGMM)":[35],"clustering":[36],"with":[38,154],"standard":[40],"pipeline":[41],"supervised":[43],"GMM-HMM":[44],"(AM)":[47],"and":[48,90,98,136,159],"n-gram":[49],"language":[50,148],"(LM)":[52],"training,":[53],"enhanced":[54],"by":[55,146,165],"scheme":[57],"re-training.":[61],"We":[62,102],"use":[63],"the":[64,87,96,131,147,162],"DPGMM":[65,166],"to":[66,95,118],"cluster":[67],"feature":[68],"vectors":[69],"into":[70],"dynamically":[72],"sized":[73],"set":[74,164],"of":[75,86,109],"units.":[77],"The":[78],"frame":[79],"based":[80,125],"class":[81,122,139],"labels":[82],"serve":[83],"as":[84,93],"transcriptions":[85],"audio":[88],"data":[89],"are":[91,152],"used":[92],"input":[94],"AM":[97],"LM":[99],"training":[100],"pipeline.":[101],"show":[103,129],"that":[104,130,137],"unsupervised":[106],"re-training":[108],"DPGMM-HMM":[111],"improves":[115],"performance":[116],"according":[117],"ABX":[120],"sound":[121,138],"discriminability":[123,140],"task":[124],"evaluation.":[126],"Our":[127,150],"results":[128],"learned":[132],"models":[133],"generalize":[134],"well":[135],"benefits":[141],"from":[142],"contextual":[143],"information":[144],"introduced":[145],"model.":[149],"systems":[151],"competitive":[153],"supervisedly":[155],"trained":[156],"phone":[157],"recognizers,":[158],"can":[160],"beat":[161],"baseline":[163],"clustering.":[167]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}