{"id":"https://openalex.org/W2116422968","doi":"https://doi.org/10.1109/icassp.2013.6639239","title":"Unsupervised discovery of linguistic structure including two-level acoustic patterns using three cascaded stages of iterative optimization","display_name":"Unsupervised discovery of linguistic structure including two-level acoustic patterns using three cascaded stages of iterative optimization","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2116422968","doi":"https://doi.org/10.1109/icassp.2013.6639239","mag":"2116422968"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639239","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5102330488","display_name":"Cheng-Tao Chung","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng-Tao Chung","raw_affiliation_strings":["Graduate Institute of Electrical Engineering, National Taiwan University, Taiwan","Grad. Inst. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Electrical Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Grad. Inst. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105193799","display_name":"Chun-an Chan","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chun-an Chan","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taiwan","[Grad. Inst. of Commun. Eng., Nat. Taiwan Univ., Taipei, Taiwan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"[Grad. Inst. of Commun. Eng., Nat. Taiwan Univ., Taipei, Taiwan]","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044010123","display_name":"Lin-shan Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Lin-shan Lee","raw_affiliation_strings":["Graduate Institute of Electrical Engineering, National Taiwan University, Taiwan","Grad. Inst. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Electrical Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Grad. Inst. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":3.4321,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.94000226,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"2","issue":null,"first_page":"8081","last_page":"8085"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9983999729156494,"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":0.9961000084877014,"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/computer-science","display_name":"Computer science","score":0.8498547673225403},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6420286297798157},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6238469481468201},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.6203345656394958},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5948548913002014},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5665326714515686},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5000560283660889},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4941087067127228},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4821419417858124},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.473201721906662},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1692635715007782}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8498547673225403},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6420286297798157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6238469481468201},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6203345656394958},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5948548913002014},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5665326714515686},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5000560283660889},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4941087067127228},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4821419417858124},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.473201721906662},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1692635715007782},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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:10.1109/icassp.2013.6639239","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W30845872","https://openalex.org/W36723659","https://openalex.org/W51277926","https://openalex.org/W87390521","https://openalex.org/W118636537","https://openalex.org/W124411215","https://openalex.org/W134006180","https://openalex.org/W308497914","https://openalex.org/W1519014771","https://openalex.org/W1606311031","https://openalex.org/W1971081490","https://openalex.org/W1983300351","https://openalex.org/W1990227353","https://openalex.org/W1991727948","https://openalex.org/W2033178790","https://openalex.org/W2083393647","https://openalex.org/W2088650673","https://openalex.org/W2099415988","https://openalex.org/W2100768664","https://openalex.org/W2101536075","https://openalex.org/W2103933358","https://openalex.org/W2109173967","https://openalex.org/W2110589736","https://openalex.org/W2111942273","https://openalex.org/W2121997342","https://openalex.org/W2159329531","https://openalex.org/W2164365067","https://openalex.org/W2164512012","https://openalex.org/W2170659185","https://openalex.org/W2293210169","https://openalex.org/W2401464865","https://openalex.org/W2403642609","https://openalex.org/W2612891210","https://openalex.org/W2915983684","https://openalex.org/W6603191899","https://openalex.org/W6605030901","https://openalex.org/W6608351678","https://openalex.org/W6610841746","https://openalex.org/W6631050791","https://openalex.org/W6675022971","https://openalex.org/W6675348038","https://openalex.org/W6677803786"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W1985458517","https://openalex.org/W2355833770","https://openalex.org/W3031039437","https://openalex.org/W183202219","https://openalex.org/W3095877357","https://openalex.org/W2072565696","https://openalex.org/W1997182898","https://openalex.org/W2944691285"],"abstract_inverted_index":{"Techniques":[0],"for":[1,34,40,104,122],"unsupervised":[2,35],"discovery":[3,36],"of":[4,14,37,61,66,113,120,183,190],"acoustic":[5,57],"patterns":[6,63,68,115],"are":[7,17,153],"getting":[8],"increasingly":[9],"attractive,":[10],"because":[11],"huge":[12],"quantities":[13],"speech":[15,47,90],"data":[16],"becoming":[18],"available":[19],"but":[20,222],"manual":[21],"annotations":[22],"remain":[23],"hard":[24],"to":[25,197,226],"acquire.":[26],"In":[27,125,145],"this":[28,146],"paper,":[29],"we":[30],"propose":[31],"an":[32,96],"approach":[33,174],"linguistic":[38,50,164],"structure":[39,51,165],"the":[41,59,70,88,137,160,163,211],"target":[42],"spoken":[43,191],"language":[44,72],"given":[45],"raw":[46],"data.":[48],"This":[49,92],"includes":[52],"two-level":[53],"(subword-like":[54],"and":[55,69,81,107,130,139,150,159],"word-like)":[56],"patterns,":[58,79],"lexicon":[60,112,138],"word-like":[62,76,114],"in":[64,156,177,204],"terms":[65],"subword-like":[67,123],"N-gram":[71],"model":[73,128,148],"based":[74],"on":[75,180,219],"patterns.":[77,124],"All":[78],"models,":[80],"parameters":[82,149],"can":[83,141],"be":[84,142],"automatically":[85],"learned":[86,167],"from":[87,135],"unlabelled":[89],"corpus.":[91],"is":[93,166,223],"achieved":[94],"by":[95,100],"initialization":[97],"step":[98],"followed":[99],"three":[101],"cascaded":[102],"stages":[103],"acoustic,":[105],"linguistic,":[106],"lexical":[108],"iterative":[109],"optimization.":[110],"The":[111,172],"defines":[116],"allowed":[117],"consecutive":[118],"sequence":[119],"HMMs":[121,140],"each":[126,157],"iteration,":[127,158],"training":[129],"decoding":[131],"produces":[132],"updated":[133],"labels":[134,152],"which":[136],"further":[143],"updated.":[144],"way,":[147],"decoded":[151],"respectively":[154],"optimized":[155],"knowledge":[161],"about":[162],"gradually":[168],"layer":[169],"after":[170],"layer.":[171],"proposed":[173,212],"was":[175],"tested":[176],"preliminary":[178],"experiments":[179],"a":[181,188,198,205],"corpus":[182],"Mandarin":[184],"broadcast":[185],"news,":[186],"including":[187],"task":[189],"term":[192],"detection":[193],"with":[194],"performance":[195,218],"compared":[196],"parallel":[199],"test":[200],"using":[201],"models":[202],"trained":[203],"supervised":[206],"way.":[207],"Results":[208],"show":[209],"that":[210],"system":[213],"not":[214],"only":[215],"yields":[216],"reasonable":[217],"its":[220],"own,":[221],"also":[224],"complimentary":[225],"existing":[227],"large":[228],"vocabulary":[229],"ASR":[230],"systems.":[231]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}