{"id":"https://openalex.org/W2463237750","doi":"https://doi.org/10.1109/taslp.2016.2582260","title":"On the Use of Acoustic Unit Discovery for Language Recognition","display_name":"On the Use of Acoustic Unit Discovery for Language Recognition","publication_year":2016,"publication_date":"2016-06-20","ids":{"openalex":"https://openalex.org/W2463237750","doi":"https://doi.org/10.1109/taslp.2016.2582260","mag":"2463237750"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2016.2582260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2582260","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5051278718","display_name":"Stephen Shum","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen H. Shum","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory Massachusetts Intitute of Technology, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2564-5214","affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory Massachusetts Intitute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004717608","display_name":"David Harwath","orcid":"https://orcid.org/0000-0003-0206-0253"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David F. Harwath","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory Massachusetts Intitute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory Massachusetts Intitute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"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/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":"Najim Dehak","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James R. Glass","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory Massachusetts Intitute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory Massachusetts Intitute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5986,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.91763392,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"24","issue":"9","first_page":"1665","last_page":"1676"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"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":0.7750886678695679},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.7169371843338013},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.7163538932800293},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5730932950973511},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5260643362998962},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5220003724098206},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.509377121925354},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5056827068328857},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5053884983062744},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.489876925945282},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48011231422424316},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4548914134502411},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3683047294616699},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3491020202636719},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.14832526445388794},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07495614886283875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7750886678695679},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.7169371843338013},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7163538932800293},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5730932950973511},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5260643362998962},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5220003724098206},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.509377121925354},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5056827068328857},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5053884983062744},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.489876925945282},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48011231422424316},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4548914134502411},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3683047294616699},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3491020202636719},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.14832526445388794},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07495614886283875},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2016.2582260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2582260","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W30845872","https://openalex.org/W202250664","https://openalex.org/W307699962","https://openalex.org/W1490504384","https://openalex.org/W1524333225","https://openalex.org/W1545920196","https://openalex.org/W1916834241","https://openalex.org/W1967924372","https://openalex.org/W2025482506","https://openalex.org/W2038810952","https://openalex.org/W2039057510","https://openalex.org/W2058641082","https://openalex.org/W2078169166","https://openalex.org/W2078769636","https://openalex.org/W2090078891","https://openalex.org/W2090958120","https://openalex.org/W2095501777","https://openalex.org/W2099415988","https://openalex.org/W2100768664","https://openalex.org/W2103133389","https://openalex.org/W2106284094","https://openalex.org/W2111732304","https://openalex.org/W2125168896","https://openalex.org/W2146194791","https://openalex.org/W2146567324","https://openalex.org/W2150769028","https://openalex.org/W2153181479","https://openalex.org/W2158069733","https://openalex.org/W2160815625","https://openalex.org/W2166637769","https://openalex.org/W2167655920","https://openalex.org/W2172287020","https://openalex.org/W2175575774","https://openalex.org/W2184045248","https://openalex.org/W2184170932","https://openalex.org/W2185814970","https://openalex.org/W2190506272","https://openalex.org/W2295880672","https://openalex.org/W2395765758","https://openalex.org/W2396707013","https://openalex.org/W2401130752","https://openalex.org/W2401464865","https://openalex.org/W2402770595","https://openalex.org/W2406215990","https://openalex.org/W2408021097","https://openalex.org/W2408208090","https://openalex.org/W2585528105","https://openalex.org/W2742703707","https://openalex.org/W2786608204","https://openalex.org/W2916510398","https://openalex.org/W2962853205","https://openalex.org/W2963620343","https://openalex.org/W3127686677","https://openalex.org/W6601311673","https://openalex.org/W6610794077","https://openalex.org/W6631362777","https://openalex.org/W6639916541","https://openalex.org/W6640010188","https://openalex.org/W6660385150","https://openalex.org/W6675022971","https://openalex.org/W6675139043","https://openalex.org/W6686429374","https://openalex.org/W6686687092","https://openalex.org/W6687442591","https://openalex.org/W6697225806","https://openalex.org/W6712239252","https://openalex.org/W6712960331","https://openalex.org/W6713378576","https://openalex.org/W6714096116","https://openalex.org/W6714336839","https://openalex.org/W6742138828","https://openalex.org/W6759825495","https://openalex.org/W6973666849"],"related_works":["https://openalex.org/W2126322296","https://openalex.org/W2955724459","https://openalex.org/W2037769829","https://openalex.org/W2163537793","https://openalex.org/W2140351598","https://openalex.org/W2916997151","https://openalex.org/W2781555308","https://openalex.org/W2402899696","https://openalex.org/W3021690593","https://openalex.org/W2125343999"],"abstract_inverted_index":{"In":[0,60],"this":[1,26,61],"paper,":[2],"we":[3,63],"explore":[4],"the":[5,48,54,127,131,152,172,187],"use":[6,77],"of":[7,57,68,88,117,151,174],"large-scale":[8],"acoustic":[9,58,81,123,149,168],"unit":[10,92],"discovery":[11,56],"for":[12,50,165],"language":[13,108,161],"recognition.":[14],"The":[15],"deep":[16,104],"neural":[17,105],"network-based":[18,106],"approaches":[19],"that":[20,113,146,160,182],"have":[21],"achieved":[22],"recent":[23],"success":[24],"in":[25,38],"task":[27],"require":[28],"transcribed":[29,140],"speech":[30],"and":[31,40,76,133,159,194],"pronunciation":[32],"dictionaries,":[33],"which":[34],"may":[35],"be":[36],"limited":[37],"availability":[39],"expensive":[41],"to":[42,46,79,101],"obtain.":[43],"We":[44,111,170],"aim":[45],"replace":[47],"need":[49],"such":[51],"supervision":[52],"via":[53],"unsupervised":[55,119],"units.":[59,169],"work,":[62],"present":[64],"a":[65,69,84,103,114,134],"parallelized":[66],"version":[67],"Bayesian":[70],"nonparametric":[71],"model":[72],"from":[73,83,192],"previous":[74],"work":[75],"it":[78],"learn":[80],"units":[82],"few":[85],"hundred":[86],"hours":[87],"multilingual":[89],"data.":[90],"These":[91],"(or":[93],"senone)":[94],"sequences":[95],"are":[96],"then":[97],"used":[98],"as":[99],"targets":[100],"train":[102],"i-vector":[107],"recognition":[109],"system.":[110],"find":[112],"score-level":[115],"fusion":[116],"our":[118,175],"system":[120,137],"with":[121],"an":[122,147],"baseline":[124,132],"can":[125,154],"shrink":[126],"gap":[128],"significantly":[129],"between":[130],"supervised":[135],"benchmark":[136],"built":[138],"using":[139],"English.":[141],"Subsequent":[142],"experiments":[143],"also":[144],"show":[145],"improved":[148],"representation":[150],"data":[153],"yield":[155],"substantial":[156],"performance":[157],"gains":[158],"specificity":[162],"is":[163],"important":[164],"discovering":[166],"meaningful":[167],"validate":[171],"generalizability":[173],"proposed":[176],"approach":[177],"by":[178],"presenting":[179],"state-of-the-art":[180],"results":[181],"exhibit":[183],"similar":[184],"trends":[185],"on":[186],"NIST":[188],"Language":[189],"Recognition":[190],"Evaluations":[191],"2011":[193],"2015.":[195]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}