{"id":"https://openalex.org/W3003558613","doi":"https://doi.org/10.1109/globalsip45357.2019.8969225","title":"Bottom-Up Unsupervised Word Discovery via Acoustic Units","display_name":"Bottom-Up Unsupervised Word Discovery via Acoustic Units","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3003558613","doi":"https://doi.org/10.1109/globalsip45357.2019.8969225","mag":"3003558613"},"language":"en","primary_location":{"id":"doi:10.1109/globalsip45357.2019.8969225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globalsip45357.2019.8969225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","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/A5045247662","display_name":"Saurabhchand Bhati","orcid":"https://orcid.org/0000-0001-6477-3895"},"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":"Saurabhchand Bhati","raw_affiliation_strings":["The Johns Hopkins University,Center for Language and Speech Processing,USA","Center for Language and Speech Processing, The Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Johns Hopkins University,Center for Language and Speech Processing,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chunxi Liu","raw_affiliation_strings":["The Johns Hopkins University,Center for Language and Speech Processing,USA","Center for Language and Speech Processing, The Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Johns Hopkins University,Center for Language and Speech Processing,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057010207","display_name":"Jes\u00fas Villalba","orcid":"https://orcid.org/0000-0001-9459-8426"},"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":"Jes\u00fas Villalba","raw_affiliation_strings":["The Johns Hopkins University,Center for Language and Speech Processing,USA","Center for Language and Speech Processing, The Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Johns Hopkins University,Center for Language and Speech Processing,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017882589","display_name":"Jan Trmal","orcid":null},"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":"Jan Trmal","raw_affiliation_strings":["The Johns Hopkins University,Center for Language and Speech Processing,USA","Center for Language and Speech Processing, The Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Johns Hopkins University,Center for Language and Speech Processing,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"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":"Sanjeev Khudanpur","raw_affiliation_strings":["The Johns Hopkins University,Center for Language and Speech Processing,USA","Center for Language and Speech Processing, The Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Johns Hopkins University,Center for Language and Speech Processing,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","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":["The Johns Hopkins University,Center for Language and Speech Processing,USA","Center for Language and Speech Processing, The Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Johns Hopkins University,Center for Language and Speech Processing,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T10028","display_name":"Topic Modeling","score":0.9980000257492065,"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":0.8171279430389404},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7590594291687012},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5305388569831848},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5287860035896301},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5202516317367554},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5176832675933838},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.506109893321991},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5058841109275818},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4648033678531647},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.364460289478302},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3231427073478699},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11512169241905212}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8171279430389404},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7590594291687012},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5305388569831848},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5287860035896301},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5202516317367554},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5176832675933838},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.506109893321991},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5058841109275818},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4648033678531647},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.364460289478302},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3231427073478699},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11512169241905212},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/globalsip45357.2019.8969225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globalsip45357.2019.8969225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W51277926","https://openalex.org/W247058069","https://openalex.org/W263845233","https://openalex.org/W1577418252","https://openalex.org/W1922655562","https://openalex.org/W2020607164","https://openalex.org/W2033413759","https://openalex.org/W2057007397","https://openalex.org/W2059652594","https://openalex.org/W2078769636","https://openalex.org/W2091746061","https://openalex.org/W2100768664","https://openalex.org/W2106284094","https://openalex.org/W2107240889","https://openalex.org/W2114347655","https://openalex.org/W2140991203","https://openalex.org/W2154093685","https://openalex.org/W2160815625","https://openalex.org/W2166637769","https://openalex.org/W2170659185","https://openalex.org/W2190506272","https://openalex.org/W2251025892","https://openalex.org/W2346964103","https://openalex.org/W2347098582","https://openalex.org/W2463237750","https://openalex.org/W2516890051","https://openalex.org/W2592866267","https://openalex.org/W2719865699","https://openalex.org/W2747192917","https://openalex.org/W2750248772","https://openalex.org/W2786608204","https://openalex.org/W2809035663","https://openalex.org/W2888872227","https://openalex.org/W2890718354","https://openalex.org/W2963230678","https://openalex.org/W2963620343","https://openalex.org/W2964169922","https://openalex.org/W6640090968","https://openalex.org/W6675022971","https://openalex.org/W6691362072"],"related_works":["https://openalex.org/W42295635","https://openalex.org/W1973996291","https://openalex.org/W2370205415","https://openalex.org/W4387493491","https://openalex.org/W2330575325","https://openalex.org/W2904225411","https://openalex.org/W4388331409","https://openalex.org/W2163803519","https://openalex.org/W2497592525","https://openalex.org/W3096145648"],"abstract_inverted_index":{"Unsupervised":[0],"term":[1,151],"discovery":[2,46,145,152],"is":[3,34,154],"the":[4,14,60,64,97,106,109,157,175,180,191,195],"task":[5],"of":[6,47,108,165,169,190],"identifying":[7],"and":[8,59,77,138],"grouping":[9],"reoccurring":[10],"word-like":[11,48,70],"patterns":[12],"from":[13,57,90,133,146],"untranscribed":[15],"audio":[16],"data.":[17,171],"It":[18],"facilitates":[19],"unsupervised":[20,45,147],"acoustic":[21,55,66,148],"model":[22,82,126],"training":[23],"in":[24],"zero":[25],"resource":[26],"setting":[27],"where":[28],"no":[29],"or":[30],"minimal":[31],"transcribed":[32],"speech":[33],"available.":[35],"In":[36],"this":[37],"paper,":[38],"we":[39,140],"investigate":[40],"two-step":[41],"bottom-up":[42,84],"approaches":[43],"for":[44,130,143],"units.":[49,71,149],"The":[50,100,150],"first":[51],"step":[52,62],"discovers":[53,118],"phone-like":[54],"units":[56],"data":[58],"second":[61],"combines":[63],"basic":[65],"blocks":[67],"to":[68,94,122],"identify":[69],"We":[72,112,186],"investigated":[73],"Embedded":[74],"Segmental":[75],"K-means":[76],"Nested":[78],"Hierarchical":[79],"Pitman-Yor":[80],"(PYR)":[81],"as":[83],"strategies.":[85],"ESK-Means":[86],"iteratively":[87],"selects":[88],"boundaries":[89,119],"an":[91],"initial":[92,110],"set":[93],"arrive":[95],"at":[96],"word":[98,131,144],"boundaries.":[99,111,124],"final":[101],"performance":[102,153],"critically":[103],"depends":[104],"on":[105,156,178,194],"quality":[107],"used":[113,129],"a":[114],"segmentation":[115,132],"method":[116],"that":[117],"much":[120],"closer":[121],"actual":[123],"PYR":[125],"has":[127],"been":[128],"space":[134],"removed":[135],"text":[136],"data,":[137],"here":[139],"use":[141],"it":[142],"evaluated":[155],"Zero":[158],"Resource":[159],"2017":[160],"challenge":[161],"dataset,":[162],"which":[163],"consists":[164],"around":[166],"70":[167],"hours":[168],"unlabelled":[170],"Our":[172],"systems":[173,177],"outperformed":[174],"baseline":[176],"all":[179],"languages":[181],"without":[182],"language-specific":[183],"parameter":[184],"tuning.":[185],"performed":[187],"comprehensive":[188],"experiments":[189],"system":[192,196],"parameters":[193],"performance.":[197]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
