{"id":"https://openalex.org/W2592866267","doi":"https://doi.org/10.1109/icassp.2017.7953169","title":"An empirical evaluation of zero resource acoustic unit discovery","display_name":"An empirical evaluation of zero resource acoustic unit discovery","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2592866267","doi":"https://doi.org/10.1109/icassp.2017.7953169","mag":"2592866267"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953169","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5069296252","display_name":"Chunxi Liu","orcid":"https://orcid.org/0000-0001-5441-9374"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Chunxi Liu","raw_affiliation_strings":["Johns Hopkins University","University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025903049","display_name":"Jinyi Yang","orcid":"https://orcid.org/0000-0001-5287-4242"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Jinyi Yang","raw_affiliation_strings":["Amazon","Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]},{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100755314","display_name":"Ming Sun","orcid":"https://orcid.org/0000-0002-8625-5199"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Sun","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008468618","display_name":"Santosh Kesiraju","orcid":"https://orcid.org/0000-0002-3725-742X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Santosh Kesiraju","raw_affiliation_strings":["International Institute of Information Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048671158","display_name":"Alena Rott","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alena Rott","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104831405","display_name":"Lucas Ondel","orcid":"https://orcid.org/0000-0003-4512-0471"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lucas Ondel","raw_affiliation_strings":["Brno University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029777844","display_name":"Pegah Ghahremani","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pegah Ghahremani","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lukas Burget","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8588,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.88906538,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5305","last_page":"5309"},"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","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"}}],"keywords":[{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7392332553863525},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7117215394973755},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5444000363349915},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5354573726654053},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.49969482421875},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48368459939956665},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47987452149391174},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.47586506605148315},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44969871640205383},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.382919043302536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3720492422580719},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3661952316761017},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1440119445323944}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7392332553863525},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7117215394973755},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5444000363349915},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5354573726654053},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.49969482421875},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48368459939956665},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47987452149391174},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.47586506605148315},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44969871640205383},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.382919043302536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3720492422580719},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3661952316761017},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1440119445323944},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7953169","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310145","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W66167291","https://openalex.org/W1516111018","https://openalex.org/W1524333225","https://openalex.org/W1880262756","https://openalex.org/W1970890968","https://openalex.org/W2001619934","https://openalex.org/W2025482506","https://openalex.org/W2057007397","https://openalex.org/W2072240081","https://openalex.org/W2078769636","https://openalex.org/W2091746061","https://openalex.org/W2100768664","https://openalex.org/W2101234009","https://openalex.org/W2113227740","https://openalex.org/W2123237149","https://openalex.org/W2126203737","https://openalex.org/W2127498532","https://openalex.org/W2142623206","https://openalex.org/W2166637769","https://openalex.org/W2168363555","https://openalex.org/W2345811097","https://openalex.org/W2347098582","https://openalex.org/W2399576818","https://openalex.org/W2402146185","https://openalex.org/W2407151108","https://openalex.org/W2407614114","https://openalex.org/W4237840503","https://openalex.org/W6602705600","https://openalex.org/W6631362777","https://openalex.org/W6639619044","https://openalex.org/W6675354045","https://openalex.org/W6676702705","https://openalex.org/W6678292227","https://openalex.org/W6712553779","https://openalex.org/W6712930963","https://openalex.org/W6713678193"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W1987128138","https://openalex.org/W2743976221"],"abstract_inverted_index":{"Acoustic":[0],"unit":[1,13,21],"discovery":[2],"(AUD)":[3],"is":[4],"a":[5,10,34,87,128],"process":[6],"of":[7,82,103,130],"automatically":[8],"identifying":[9],"categorical":[11],"acoustic":[12,20,30,59],"inventory":[14],"from":[15],"speech":[16,44,109],"and":[17,42,78,111],"producing":[18],"corresponding":[19],"tokenizations.":[22],"AUD":[23,52,104,117],"provides":[24],"an":[25,74],"important":[26],"avenue":[27],"for":[28],"unsupervised":[29,75],"model":[31],"training":[32],"in":[33,54,73,137],"zero":[35,139],"resource":[36,140],"setting":[37],"where":[38],"expert-provided":[39],"linguistic":[40],"knowledge":[41],"transcribed":[43],"are":[45,119],"unavailable.":[46],"Therefore,":[47],"to":[48,93],"further":[49],"facilitate":[50],"zero-resource":[51],"process,":[53],"this":[55],"paper,":[56],"we":[57,99],"demonstrate":[58],"feature":[60,91],"representations":[61],"can":[62,134],"be":[63,135],"significantly":[64],"improved":[65],"by":[66],"(i)":[67],"performing":[68],"linear":[69],"discriminant":[70],"analysis":[71],"(LDA)":[72],"self-trained":[76],"fashion,":[77],"(ii)":[79],"leveraging":[80],"resources":[81,125,133],"other":[83],"languages":[84],"through":[85],"building":[86],"multilingual":[88],"bottleneck":[89],"(BN)":[90],"extractor":[92],"give":[94],"effective":[95],"cross-lingual":[96],"generalization.":[97],"Moreover,":[98],"perform":[100],"comprehensive":[101],"evaluations":[102,118],"efficacy":[105],"on":[106],"multiple":[107],"downstream":[108],"applications,":[110],"their":[112],"correlated":[113],"performance":[114],"suggests":[115],"that":[116],"feasible":[120],"using":[121],"different":[122],"alternative":[123],"language":[124],"when":[126],"only":[127],"subset":[129],"these":[131],"evaluation":[132],"available":[136],"typical":[138],"applications.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}