{"id":"https://openalex.org/W2787447541","doi":"https://doi.org/10.1109/asru.2017.8269011","title":"Feature optimized DPGMM clustering for unsupervised subword modeling: A contribution to zerospeech 2017","display_name":"Feature optimized DPGMM clustering for unsupervised subword modeling: A contribution to zerospeech 2017","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2787447541","doi":"https://doi.org/10.1109/asru.2017.8269011","mag":"2787447541"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2017.8269011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8269011","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","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":true,"raw_author_name":"Michael Heck","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, 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/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":["Graduate School of Information Science, Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, 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":["Graduate School of Information Science, Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5015873217"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":6.437,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.97202412,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"740","last_page":"746"},"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":0.998199999332428,"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":0.9973999857902527,"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":0.8209943771362305},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6197506785392761},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5660386681556702},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5249947309494019},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5044554471969604},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.48772916197776794},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.47599518299102783},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.47417938709259033},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.47045767307281494},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.42594239115715027},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.42367318272590637},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4217013716697693},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4196200966835022},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3154982626438141},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0877566933631897}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8209943771362305},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6197506785392761},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5660386681556702},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5249947309494019},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5044554471969604},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.48772916197776794},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.47599518299102783},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.47417938709259033},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.47045767307281494},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.42594239115715027},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.42367318272590637},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4217013716697693},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4196200966835022},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3154982626438141},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0877566933631897},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2017.8269011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8269011","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7099999785423279,"display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1599512239","https://openalex.org/W1631260214","https://openalex.org/W1796128977","https://openalex.org/W2001619934","https://openalex.org/W2002342963","https://openalex.org/W2019042707","https://openalex.org/W2078769636","https://openalex.org/W2106554350","https://openalex.org/W2113641473","https://openalex.org/W2124629003","https://openalex.org/W2128032727","https://openalex.org/W2345811097","https://openalex.org/W2395899413","https://openalex.org/W2396043527","https://openalex.org/W2399576818","https://openalex.org/W2404799143","https://openalex.org/W2509930204","https://openalex.org/W2586754519","https://openalex.org/W2786608204","https://openalex.org/W2963620343","https://openalex.org/W6631362777","https://openalex.org/W6638159135","https://openalex.org/W6678947187","https://openalex.org/W6704305767","https://openalex.org/W6712202099","https://openalex.org/W6712444837","https://openalex.org/W6712553779","https://openalex.org/W6713256719","https://openalex.org/W6973666849"],"related_works":["https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2155033763","https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2370972896","https://openalex.org/W2160650576","https://openalex.org/W2501000458","https://openalex.org/W2048014685"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"our":[3,135],"unsupervised":[4],"subword":[5,101,121],"modeling":[6,102],"pipeline":[7,156],"for":[8,161],"the":[9,21,66,91,100,106,109,115,140],"zero":[10],"resource":[11],"speech":[12,33,50],"challenge":[13],"(ZeroSpeech)":[14],"2017.":[15],"Our":[16,155],"approach":[17],"is":[18,165],"built":[19],"around":[20],"Dirichlet":[22],"process":[23],"Gaussian":[24],"mixture":[25],"model":[26],"(DPGMM)":[27],"that":[28,95],"we":[29,77,118],"use":[30],"to":[31,87,105,123],"cluster":[32],"feature":[34],"vectors":[35],"into":[36],"a":[37,72,128,151],"dynamically":[38],"sized":[39],"set":[40,130],"of":[41,56,131,142,153],"classes.":[42],"By":[43],"considering":[44],"each":[45],"class":[46,57],"an":[47],"acoustic":[48],"unit,":[49],"can":[51],"be":[52],"represented":[53],"as":[54,175],"sequence":[55],"posteriorgrams.":[58],"We":[59,93,133],"enhance":[60],"this":[61,96],"method":[62],"by":[63],"automatically":[64],"optimizing":[65],"DPGMM":[67],"sampler's":[68],"input":[69],"features":[70],"in":[71,90,147],"multi-stage":[73],"clustering":[74],"framework,":[75],"where":[76],"unsupervisedly":[78],"learn":[79],"transformations":[80],"using":[81],"LDA,":[82],"MLLT":[83],"and":[84,139,164],"(basis)":[85],"fMLLR":[86],"reduce":[88],"variance":[89],"features.":[92],"show":[94],"optimization":[97],"considerably":[98],"boosts":[99],"quality,":[103],"according":[104],"performance":[107],"on":[108,150],"ABX":[110],"phone":[111],"discriminability":[112],"task.":[113],"For":[114],"first":[116],"time,":[117],"apply":[119],"inferred":[120],"models":[122],"previously":[124],"unseen":[125],"data":[126],"from":[127],"new":[129],"speakers.":[132],"demonstrate":[134],"method's":[136],"good":[137],"generalization":[138],"effectiveness":[141],"its":[143],"blind":[144],"speaker":[145,183],"adaptation":[146],"extensive":[148],"experiments":[149],"multitude":[152],"datasets.":[154],"has":[157],"very":[158],"little":[159],"need":[160],"hyper-parameter":[162],"adjustment":[163],"entirely":[166],"unsupervised,":[167],"i.e.,":[168],"it":[169],"only":[170],"takes":[171],"raw":[172],"audio":[173],"recordings":[174],"input,":[176],"without":[177],"requiring":[178],"any":[179],"pre-defined":[180],"segmentation,":[181],"explicit":[182],"IDs":[184],"or":[185],"other":[186],"meta":[187],"data.":[188]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}