{"id":"https://openalex.org/W1997505733","doi":"https://doi.org/10.1109/slt.2014.7078557","title":"Unsupervised lexical clustering of speech segments using fixed-dimensional acoustic embeddings","display_name":"Unsupervised lexical clustering of speech segments using fixed-dimensional acoustic embeddings","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W1997505733","doi":"https://doi.org/10.1109/slt.2014.7078557","mag":"1997505733"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2014.7078557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/6f530e02-31ae-4414-8edf-a6d8a11f5852","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":true,"raw_author_name":"Herman Kamper","raw_affiliation_strings":["CSTR","ILCC, University of Edinburgh, UK","[CSTR, School of Informatics, University of Edinburgh, UK]"],"affiliations":[{"raw_affiliation_string":"CSTR","institution_ids":[]},{"raw_affiliation_string":"ILCC, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"[CSTR, School of Informatics, University of Edinburgh, UK]","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/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":["HLTCOE and CLSP, Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"HLTCOE and CLSP, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"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":"Simon King","raw_affiliation_strings":["CSTR","[CSTR, School of Informatics, University of Edinburgh, UK]"],"affiliations":[{"raw_affiliation_string":"CSTR","institution_ids":[]},{"raw_affiliation_string":"[CSTR, School of Informatics, University of Edinburgh, UK]","institution_ids":["https://openalex.org/I98677209"]}]},{"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":["ILCC, University of Edinburgh, UK","ILCC, School of Informatics, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"ILCC, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"ILCC, School of Informatics, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040305929"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":5.9082,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.96095689,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"100","last_page":"105"},"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":0.9993000030517578,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech 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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8473366498947144},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7630374431610107},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.625423789024353},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.5231080055236816},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5017669200897217},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.48875951766967773},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.45155537128448486},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.4513617157936096},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44663119316101074},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39334747195243835},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16842198371887207}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8473366498947144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7630374431610107},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.625423789024353},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5231080055236816},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5017669200897217},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.48875951766967773},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.45155537128448486},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.4513617157936096},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44663119316101074},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39334747195243835},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16842198371887207},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/slt.2014.7078557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.724.7106","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.724.7106","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.ed.ac.uk/downloads/publications/2014/kamper%2Bjansen%2Bking%2Bgoldwater_slt2014.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/6f530e02-31ae-4414-8edf-a6d8a11f5852","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/6f530e02-31ae-4414-8edf-a6d8a11f5852","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, King, S & Goldwater, S 2014, Unsupervised lexical clustering of speech segments using fixed dimensional acoustic embeddings. in Proceedings of the IEEE Spoken Language Technology Workshop. Institute of Electrical and Electronics Engineers.","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/6f530e02-31ae-4414-8edf-a6d8a11f5852","is_oa":false,"landing_page_url":"https://hdl.handle.net/20.500.11820/6f530e02-31ae-4414-8edf-a6d8a11f5852","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:pure.ed.ac.uk:openaire/6f530e02-31ae-4414-8edf-a6d8a11f5852","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/6f530e02-31ae-4414-8edf-a6d8a11f5852","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, King, S & Goldwater, S 2014, Unsupervised lexical clustering of speech segments using fixed dimensional acoustic embeddings. in Proceedings of the IEEE Spoken Language Technology Workshop. Institute of Electrical and Electronics Engineers.","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7400000095367432}],"awards":[{"id":"https://openalex.org/G4055593462","display_name":null,"funder_award_id":"EP/I031022/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W30845872","https://openalex.org/W51277926","https://openalex.org/W1503398984","https://openalex.org/W1590183771","https://openalex.org/W1967924372","https://openalex.org/W1987302197","https://openalex.org/W2010188467","https://openalex.org/W2020607164","https://openalex.org/W2022058071","https://openalex.org/W2025482506","https://openalex.org/W2033413759","https://openalex.org/W2057007397","https://openalex.org/W2059652594","https://openalex.org/W2100768664","https://openalex.org/W2101234009","https://openalex.org/W2107038463","https://openalex.org/W2107240889","https://openalex.org/W2108622839","https://openalex.org/W2113054345","https://openalex.org/W2120636621","https://openalex.org/W2126203737","https://openalex.org/W2126377586","https://openalex.org/W2138615112","https://openalex.org/W2140277151","https://openalex.org/W2140991203","https://openalex.org/W2142119958","https://openalex.org/W2166270474","https://openalex.org/W2168277610","https://openalex.org/W2407151108","https://openalex.org/W2799046698","https://openalex.org/W2950511172","https://openalex.org/W6601311673","https://openalex.org/W6675022971","https://openalex.org/W6675354045","https://openalex.org/W6675966832","https://openalex.org/W6676028815","https://openalex.org/W6678007500","https://openalex.org/W6680970901"],"related_works":["https://openalex.org/W2140536630","https://openalex.org/W2391730868","https://openalex.org/W2759814045","https://openalex.org/W2118055728","https://openalex.org/W2736760277","https://openalex.org/W4386940087","https://openalex.org/W4386931226","https://openalex.org/W2184188632","https://openalex.org/W2153899490","https://openalex.org/W4390417714"],"abstract_inverted_index":{"Unsupervised":[0],"speech":[1,11,139],"processing":[2,140],"methods":[3,78],"are":[4,55],"essential":[5],"for":[6],"applications":[7],"ranging":[8],"from":[9],"zero-resource":[10],"technology":[12],"to":[13,43,112],"modelling":[14],"child":[15],"language":[16],"acquisition.":[17],"One":[18],"challenging":[19],"problem":[20],"is":[21,33,65,95,110],"discovering":[22],"the":[23,27,29,34,76,105,133],"word":[24,40,53],"inventory":[25],"of":[26,36,107,114,127],"language:":[28],"lexicon.":[30],"Lexical":[31],"clustering":[32,50,64,71,126,135],"task":[35],"grouping":[37],"unlabelled":[38],"acoustic":[39,60],"tokens":[41],"according":[42],"type.":[44],"We":[45,68,122],"propose":[46],"a":[47,58],"novel":[48],"lexical":[49,134],"model:":[51],"variable-length":[52],"segments":[54],"embedded":[56],"in":[57,62,84,88,137],"fixed-dimensional":[59,128],"space":[61],"which":[63,102],"then":[66],"performed.":[67],"evaluate":[69],"several":[70],"algorithms":[72],"and":[73,118],"find":[74],"that":[75,113,124],"best":[77,92],"produce":[79],"clusters":[80],"with":[81],"wide":[82],"variation":[83],"sizes,":[85],"as":[86,132],"observed":[87],"natural":[89],"language.":[90],"The":[91],"probabilistic":[93],"approach":[94],"an":[96],"infinite":[97],"Gaussian":[98],"mixture":[99],"model":[100],"(IGMM),":[101],"automatically":[103],"chooses":[104],"number":[106],"clusters.":[108],"Performance":[109],"comparable":[111],"non-probabilistic":[115],"Chinese":[116],"Whispers":[117],"average-linkage":[119],"hierarchical":[120],"clustering.":[121],"conclude":[123],"IGMM":[125],"embeddings":[129],"holds":[130],"promise":[131],"component":[136],"unsupervised":[138],"systems.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}