{"id":"https://openalex.org/W2295297373","doi":"https://doi.org/10.1109/taslp.2016.2517567","title":"Unsupervised Word Segmentation and Lexicon Discovery Using Acoustic Word Embeddings","display_name":"Unsupervised Word Segmentation and Lexicon Discovery Using Acoustic Word Embeddings","publication_year":2016,"publication_date":"2016-01-12","ids":{"openalex":"https://openalex.org/W2295297373","doi":"https://doi.org/10.1109/taslp.2016.2517567","mag":"2295297373"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2016.2517567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2517567","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1603.02845","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040305929","display_name":"Herman Kamper","orcid":"https://orcid.org/0000-0003-2980-3475"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Herman Kamper","raw_affiliation_strings":["School of Informatics, University of Edinburgh, Edinburgh, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103622427","display_name":"Aren Jansen","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"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":"Aren Jansen","raw_affiliation_strings":["Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","Machine Hearing Group, Google, Inc., Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Machine Hearing Group, Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075564798","display_name":"Sharon Goldwater","orcid":"https://orcid.org/0000-0002-7298-0947"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sharon Goldwater","raw_affiliation_strings":["School of Informatics, University of Edinburgh, Edinburgh, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":21.9121,"has_fulltext":true,"cited_by_count":75,"citation_normalized_percentile":{"value":0.99273342,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":"24","issue":"4","first_page":"669","last_page":"679"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9993000030517578,"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/word","display_name":"Word (group theory)","score":0.7275370955467224},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.7049857378005981},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6362261772155762},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6101009845733643},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5717133283615112},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.5345085859298706},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43694016337394714},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.42025497555732727},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.34187382459640503}],"concepts":[{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7275370955467224},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.7049857378005981},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6362261772155762},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6101009845733643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5717133283615112},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.5345085859298706},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43694016337394714},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.42025497555732727},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.34187382459640503},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/taslp.2016.2517567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2517567","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"},{"id":"pmh:oai:arXiv.org:1603.02845","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1603.02845","pdf_url":"https://arxiv.org/pdf/1603.02845","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:publications/210d74be-006b-495d-b182-14801b3b3ba6","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/210d74be-006b-495d-b182-14801b3b3ba6","pdf_url":"https://www.research.ed.ac.uk/files/23728739/Goldwater_Kamper_et_al_2016.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Kamper, H, Jansen, A & Goldwater, S 2016, 'Unsupervised Word Segmentation and Lexicon Discovery Using Acoustic Word Embeddings', IEEE Transactions on Audio, Speech and Language Processing, vol. 24, no. 4, pp. 669-679. https://doi.org/10.1109/TASLP.2016.2517567","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/210d74be-006b-495d-b182-14801b3b3ba6","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/210d74be-006b-495d-b182-14801b3b3ba6","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Kamper, H, Jansen, A & Goldwater, S 2016, 'Unsupervised Word Segmentation and Lexicon Discovery Using Acoustic Word Embeddings', IEEE Transactions on Audio, Speech and Language Processing, vol. 24, no. 4, pp. 669-679. https://doi.org/10.1109/TASLP.2016.2517567","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.ed.ac.uk:publications/210d74be-006b-495d-b182-14801b3b3ba6","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11820/210d74be-006b-495d-b182-14801b3b3ba6","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1603.02845","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1603.02845","pdf_url":"https://arxiv.org/pdf/1603.02845","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7799999713897705}],"awards":[{"id":"https://openalex.org/G8323132575","display_name":null,"funder_award_id":"EP/H050442/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320306183","display_name":"James S. McDonnell Foundation","ror":"https://ror.org/03dy4aq19"},{"id":"https://openalex.org/F4320320351","display_name":"Commonwealth Scholarship Commission","ror":"https://ror.org/051x4wh35"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W52412328","https://openalex.org/W178496478","https://openalex.org/W1503398984","https://openalex.org/W1525748279","https://openalex.org/W1539673959","https://openalex.org/W1577418252","https://openalex.org/W1590183771","https://openalex.org/W1606268232","https://openalex.org/W1778492285","https://openalex.org/W1942713348","https://openalex.org/W1967924372","https://openalex.org/W1997505733","https://openalex.org/W2010188467","https://openalex.org/W2022058071","https://openalex.org/W2032943813","https://openalex.org/W2033413759","https://openalex.org/W2036964623","https://openalex.org/W2057007397","https://openalex.org/W2059652594","https://openalex.org/W2072396742","https://openalex.org/W2074546930","https://openalex.org/W2097308346","https://openalex.org/W2099873701","https://openalex.org/W2100768664","https://openalex.org/W2104290444","https://openalex.org/W2107038463","https://openalex.org/W2114347655","https://openalex.org/W2116330964","https://openalex.org/W2116422968","https://openalex.org/W2120636621","https://openalex.org/W2126203737","https://openalex.org/W2126377586","https://openalex.org/W2140991203","https://openalex.org/W2142390309","https://openalex.org/W2152131029","https://openalex.org/W2152483743","https://openalex.org/W2154093685","https://openalex.org/W2157427027","https://openalex.org/W2161952424","https://openalex.org/W2166270474","https://openalex.org/W2166391802","https://openalex.org/W2168277610","https://openalex.org/W2190506272","https://openalex.org/W2398490608","https://openalex.org/W2799046698","https://openalex.org/W2952155034","https://openalex.org/W2952343510","https://openalex.org/W2997701990","https://openalex.org/W6602180557","https://openalex.org/W6607261905","https://openalex.org/W6638059883","https://openalex.org/W6640777149","https://openalex.org/W6675002571","https://openalex.org/W6675022971","https://openalex.org/W6675747103","https://openalex.org/W6676028815","https://openalex.org/W6678007500","https://openalex.org/W6687508285"],"related_works":["https://openalex.org/W3136209078","https://openalex.org/W2978383222","https://openalex.org/W2172629291","https://openalex.org/W2380773642","https://openalex.org/W2384559435","https://openalex.org/W2337707338","https://openalex.org/W2393940967","https://openalex.org/W2058548953","https://openalex.org/W2785359773","https://openalex.org/W2385598138"],"abstract_inverted_index":{"In":[0,33,83],"settings":[1],"where":[2],"only":[3],"unlabeled":[4,56],"speech":[5,9,45,57,76],"data":[6],"is":[7,26,68,93],"available,":[8],"technology":[10],"needs":[11,39],"to":[12,40,139,162],"be":[13,41],"developed":[14],"without":[15],"transcriptions,":[16],"pronunciation":[17],"dictionaries,":[18],"or":[19],"language":[20,31],"modelling":[21],"text.":[22],"A":[23],"similar":[24],"problem":[25],"faced":[27],"when":[28],"modeling":[29],"infant":[30],"acquisition.":[32],"these":[34],"cases,":[35],"categorical":[36],"linguistic":[37],"structure":[38],"discovered":[42,80],"directly":[43],"from":[44],"audio.":[46],"We":[47,121],"present":[48],"a":[49,69,86,96,105,110,127,151,170],"novel":[50],"unsupervised":[51,71,136],"Bayesian":[52],"model":[53,113,144,166],"that":[54],"segments":[55,61],"and":[58],"clusters":[59],"the":[60,74,135,163],"into":[62],"hypothesized":[63],"word":[64,81,88,123],"groupings.":[65],"The":[66,101,143],"result":[67],"complete":[70],"tokenization":[72],"of":[73,79],"input":[75],"in":[77,95,114,126,160],"terms":[78],"types.":[82],"our":[84,165],"approach,":[85],"potential":[87],"segment":[89],"(of":[90],"arbitrary":[91],"length)":[92],"embedded":[94],"fixed-dimensional":[97],"acoustic":[98,112],"vector":[99],"space.":[100],"model,":[102],"implemented":[103],"as":[104],"Gibbs":[106],"sampler,":[107],"then":[108],"builds":[109],"whole-word":[111],"this":[115],"space":[116],"while":[117],"jointly":[118],"performing":[119],"segmentation.":[120],"report":[122],"error":[124,148],"rates":[125],"small-vocabulary":[128],"connected":[129],"digit":[130],"recognition":[131],"task":[132],"by":[133,155],"mapping":[134],"decoded":[137],"output":[138],"ground":[140],"truth":[141],"transcriptions.":[142],"achieves":[145],"around":[146],"20%":[147],"rate,":[149],"outperforming":[150],"previous":[152],"HMM-based":[153],"system":[154],"about":[156],"10%":[157],"absolute.":[158],"Moreover,":[159],"contrast":[161],"baseline,":[164],"does":[167],"not":[168],"require":[169],"pre-specified":[171],"vocabulary":[172],"size.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":14},{"year":2016,"cited_by_count":4}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2021-02-01T00:00:00"}