{"id":"https://openalex.org/W2780786457","doi":"https://doi.org/10.1587/transinf.2017edp7175","title":"Learning Supervised Feature Transformations on Zero Resources for Improved Acoustic Unit Discovery","display_name":"Learning Supervised Feature Transformations on Zero Resources for Improved Acoustic Unit Discovery","publication_year":2017,"publication_date":"2017-12-31","ids":{"openalex":"https://openalex.org/W2780786457","doi":"https://doi.org/10.1587/transinf.2017edp7175","mag":"2780786457"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2017edp7175","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2017edp7175","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E101.D/1/E101.D_2017EDP7175/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E101.D/1/E101.D_2017EDP7175/_pdf","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":["Augmented Human Communication Laboratory, Graduate School of Information Science, Nara Institute of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Augmented Human Communication Laboratory, Graduate School of Information Science, Nara Institute of Science and Technology","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, Graduate School of Information Science, Nara Institute of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Augmented Human Communication Laboratory, Graduate School of Information Science, Nara Institute of Science and Technology","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, Graduate School of Information Science, Nara Institute of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Augmented Human Communication Laboratory, Graduate School of Information Science, Nara Institute of Science and Technology","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":0.7462,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.7320711,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"E101.D","issue":"1","first_page":"205","last_page":"214"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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":0.9987999796867371,"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":0.9984999895095825,"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":0.7817027568817139},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6266241073608398},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6065433025360107},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.598347008228302},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5602343082427979},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5328959226608276},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4996767044067383},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.45491811633110046},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4250807762145996},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4141850471496582},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.41208624839782715},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.16524815559387207}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7817027568817139},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6266241073608398},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6065433025360107},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.598347008228302},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5602343082427979},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5328959226608276},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4996767044067383},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.45491811633110046},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4250807762145996},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4141850471496582},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.41208624839782715},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.16524815559387207},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2017edp7175","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2017edp7175","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E101.D/1/E101.D_2017EDP7175/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2017edp7175","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2017edp7175","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E101.D/1/E101.D_2017EDP7175/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/10"}],"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/G1688345242","display_name":null,"funder_award_id":"17H06101","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/G4227499671","display_name":null,"funder_award_id":"KAKENHI Grant","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/G4827429566","display_name":null,"funder_award_id":"Grant Numbers","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5786340949","display_name":null,"funder_award_id":"KAKENHI Grant Number","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"},{"id":"https://openalex.org/G8430481527","display_name":null,"funder_award_id":"Number","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8777250574","display_name":"Research for unsupervised acoustic pattern discovery with zero resources","funder_award_id":"17K00237","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G947068629","display_name":null,"funder_award_id":"JP17K00237","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/W2780786457.pdf","grobid_xml":"https://content.openalex.org/works/W2780786457.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W66167291","https://openalex.org/W1524333225","https://openalex.org/W1796128977","https://openalex.org/W1997505733","https://openalex.org/W2001619934","https://openalex.org/W2002342963","https://openalex.org/W2044138293","https://openalex.org/W2064210461","https://openalex.org/W2071128523","https://openalex.org/W2106554350","https://openalex.org/W2114347655","https://openalex.org/W2117041980","https://openalex.org/W2118841860","https://openalex.org/W2119187236","https://openalex.org/W2124629003","https://openalex.org/W2126203737","https://openalex.org/W2128032727","https://openalex.org/W2145410271","https://openalex.org/W2294798173","https://openalex.org/W2395899413","https://openalex.org/W2396043527","https://openalex.org/W2399576818","https://openalex.org/W2402014506","https://openalex.org/W2404799143","https://openalex.org/W2963620343","https://openalex.org/W4302557958"],"related_works":["https://openalex.org/W2250488071","https://openalex.org/W2356150353","https://openalex.org/W2075383893","https://openalex.org/W2353313924","https://openalex.org/W1481704333","https://openalex.org/W2786094008","https://openalex.org/W3131501806","https://openalex.org/W2799683370","https://openalex.org/W2807745940","https://openalex.org/W2515319207"],"abstract_inverted_index":{"In":[0],"this":[1,69],"work":[2],"we":[3,71,124],"utilize":[4,72],"feature":[5,41,113,137],"transformations":[6,37,138,149],"that":[7,43,146,188],"are":[8,44],"common":[9],"in":[10,62,139,155],"supervised":[11,133],"learning":[12,95,134],"without":[13],"having":[14],"prior":[15],"supervision,":[16],"with":[17],"the":[18,86,121,147,152,161,164,168],"goal":[19],"to":[20,39,59,79,135,160],"improve":[21,193],"Dirichlet":[22],"process":[23],"Gaussian":[24],"mixture":[25],"model":[26,129],"(DPGMM)":[27],"based":[28,82,112],"acoustic":[29,128],"unit":[30],"discovery.":[31],"The":[32,49,89,115],"motivation":[33],"of":[34,51,76,117,163,183],"using":[35],"such":[36,189],"is":[38,120],"create":[40],"vectors":[42],"more":[45],"suitable":[46],"for":[47,53,85,94,132,179],"clustering.":[48],"need":[50],"labels":[52,84,90],"these":[54],"methods":[55],"makes":[56],"it":[57],"difficult":[58],"use":[60,125],"them":[61],"a":[63,73,126,140,177],"zero":[64,141],"resource":[65,142],"setting.":[66],"To":[67],"overcome":[68],"issue":[70],"first":[74],"iteration":[75],"DPGMM":[77,153,165],"clustering":[78],"generate":[80],"frame":[81],"class":[83,171,195],"target":[87],"data.":[88],"serve":[91],"as":[92],"basis":[93],"linear":[96,102,109],"discriminant":[97],"analysis":[98],"(LDA),":[99],"maximum":[100,107],"likelihood":[101,108],"transform":[103],"(MLLT)":[104],"and":[105,186],"feature-space":[106],"regression":[110],"(fMLLR)":[111],"transformations.":[114],"novelty":[116],"our":[118],"approach":[119],"way":[122],"how":[123],"traditional":[127],"training":[130],"pipeline":[131],"estimate":[136],"scenario.":[143],"We":[144,174],"show":[145],"learned":[148],"greatly":[150],"support":[151],"sampler":[154],"finding":[156],"better":[157],"clusters,":[158],"according":[159],"performance":[162],"posteriorgrams":[166],"on":[167],"ABX":[169],"sound":[170,194],"discriminability":[172],"task.":[173],"also":[175],"introduce":[176],"method":[178],"combining":[180],"posteriorgram":[181],"outputs":[182],"multiple":[184],"clusterings":[185],"demonstrate":[187],"combinations":[190],"can":[191],"further":[192],"discriminability.":[196]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}