{"id":"https://openalex.org/W2599585580","doi":"https://doi.org/10.1109/asru.2017.8269008","title":"An embedded segmental K-means model for unsupervised segmentation and clustering of speech","display_name":"An embedded segmental K-means model for unsupervised segmentation and clustering of speech","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2599585580","doi":"https://doi.org/10.1109/asru.2017.8269008","mag":"2599585580"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2017.8269008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8269008","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1703.08135","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/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Herman Kamper","raw_affiliation_strings":["Electrical and Electronic Engineering, Stellenbosch University, South Africa","Electrical and Electronic Engineering, Stellenbosch University, South-Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Electronic Engineering, Stellenbosch University, South Africa","institution_ids":["https://openalex.org/I26092322"]},{"raw_affiliation_string":"Electrical and Electronic Engineering, Stellenbosch University, South-Africa","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015602781","display_name":"Karen Livescu","orcid":"https://orcid.org/0000-0003-4962-946X"},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karen Livescu","raw_affiliation_strings":["Toyota Technological Institute, Chicago, United States","[Toyota Technological Institute at Chicago, United States]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute, Chicago, United States","institution_ids":["https://openalex.org/I160992636"]},{"raw_affiliation_string":"[Toyota Technological Institute at Chicago, United States]","institution_ids":["https://openalex.org/I160992636"]}]},{"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, United Kingdom","ILCC, School of Informatics, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ILCC, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"ILCC, School of Informatics, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"719","last_page":"726"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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/T10860","display_name":"Speech and Audio Processing","score":0.9980000257492065,"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/k-means-clustering","display_name":"k-means clustering","score":0.7267636060714722},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7134883403778076},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6925361752510071},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5753363966941833},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.5618438720703125},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5520583987236023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5233687162399292},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4826803505420685},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46854838728904724},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42952072620391846},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.41948583722114563}],"concepts":[{"id":"https://openalex.org/C207968372","wikidata":"https://www.wikidata.org/wiki/Q310401","display_name":"k-means clustering","level":3,"score":0.7267636060714722},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7134883403778076},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6925361752510071},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5753363966941833},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.5618438720703125},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5520583987236023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5233687162399292},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4826803505420685},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46854838728904724},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42952072620391846},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.41948583722114563}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/asru.2017.8269008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8269008","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1703.08135","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.08135","pdf_url":"https://arxiv.org/pdf/1703.08135","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:openaire/b85f03fb-6794-4eac-8c0b-d7c043f2108c","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/b85f03fb-6794-4eac-8c0b-d7c043f2108c","pdf_url":"https://www.research.ed.ac.uk/files/80754661/An_embedded_segmental_k_means_KAMPER_DoA310817_AFV.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, Livescu, K & Goldwater, S 2018, An embedded segmental K-means model for unsupervised segmentation and clustering of speech. in 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)., 17525302, Institute of Electrical and Electronics Engineers, pp. 719-726, 2017 IEEE Automatic Speech Recognition and Understanding Workshop , Okinawa, Japan, 16/12/17. https://doi.org/10.1109/ASRU.2017.8269008","raw_type":"contributionToPeriodical"},{"id":"mag:2599585580","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1703.08135.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:pure.ed.ac.uk:publications/b85f03fb-6794-4eac-8c0b-d7c043f2108c","is_oa":true,"landing_page_url":"https://ieeexplore.ieee.org/document/8269008","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, Livescu, K & Goldwater, S 2018, An embedded segmental K-means model for unsupervised segmentation and clustering of speech. in 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)., 17525302, Institute of Electrical and Electronics Engineers, pp. 719-726, 2017 IEEE Automatic Speech Recognition and Understanding Workshop , Okinawa, Japan, 16/12/17. https://doi.org/10.1109/ASRU.2017.8269008","raw_type":"contributionToPeriodical"},{"id":"doi:10.48550/arxiv.1703.08135","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1703.08135","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1703.08135","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.08135","pdf_url":"https://arxiv.org/pdf/1703.08135","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":[],"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/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":55,"referenced_works":["https://openalex.org/W51277926","https://openalex.org/W113159538","https://openalex.org/W1577418252","https://openalex.org/W1590183771","https://openalex.org/W1778492285","https://openalex.org/W1796128977","https://openalex.org/W2010188467","https://openalex.org/W2020607164","https://openalex.org/W2022058071","https://openalex.org/W2032943813","https://openalex.org/W2048648518","https://openalex.org/W2057007397","https://openalex.org/W2059652594","https://openalex.org/W2072396742","https://openalex.org/W2091746061","https://openalex.org/W2100768664","https://openalex.org/W2114347655","https://openalex.org/W2116330964","https://openalex.org/W2117041980","https://openalex.org/W2142775654","https://openalex.org/W2143776582","https://openalex.org/W2154093685","https://openalex.org/W2161562001","https://openalex.org/W2190506272","https://openalex.org/W2251025892","https://openalex.org/W2291770225","https://openalex.org/W2295297373","https://openalex.org/W2346964103","https://openalex.org/W2398490608","https://openalex.org/W2463237750","https://openalex.org/W2468716020","https://openalex.org/W2483390977","https://openalex.org/W2516890051","https://openalex.org/W2550241133","https://openalex.org/W2641832364","https://openalex.org/W2686360660","https://openalex.org/W2719865699","https://openalex.org/W2758697525","https://openalex.org/W2951216052","https://openalex.org/W2962736743","https://openalex.org/W2962980711","https://openalex.org/W2963311389","https://openalex.org/W2963571336","https://openalex.org/W3102667484","https://openalex.org/W6638059883","https://openalex.org/W6638159135","https://openalex.org/W6675022971","https://openalex.org/W6677180724","https://openalex.org/W6677620606","https://openalex.org/W6681031197","https://openalex.org/W6691362072","https://openalex.org/W6704726871","https://openalex.org/W6712720595","https://openalex.org/W6731763572","https://openalex.org/W6973666849"],"related_works":["https://openalex.org/W2964169922","https://openalex.org/W2293362876","https://openalex.org/W3176613769","https://openalex.org/W2042379175","https://openalex.org/W2251049652","https://openalex.org/W1495279923","https://openalex.org/W1653341947","https://openalex.org/W2138136853","https://openalex.org/W2152213375","https://openalex.org/W3132188589","https://openalex.org/W2950854713","https://openalex.org/W2327469985","https://openalex.org/W2896360867","https://openalex.org/W2948981205","https://openalex.org/W2110952388","https://openalex.org/W2769159728","https://openalex.org/W2950561535","https://openalex.org/W2889205371","https://openalex.org/W2783844464","https://openalex.org/W3087258756"],"abstract_inverted_index":{"Unsupervised":[0],"segmentation":[1,78],"and":[2,77,113,118],"clustering":[3,76],"of":[4,121,155,175],"unlabelled":[5],"speech":[6,12,52],"are":[7,150],"core":[8],"problems":[9],"in":[10,39,129],"zero-resource":[11],"processing.":[13],"Most":[14],"approaches":[15,109],"lie":[16],"at":[17],"methodological":[18],"extremes:":[19],"some":[20],"use":[21],"probabilistic":[22],"Bayesian":[23,44,61,82,86,137],"models":[24],"with":[25,144],"convergence":[26],"guarantees,":[27],"while":[28,139],"others":[29],"opt":[30],"for":[31],"more":[32],"efficient":[33],"heuristic":[34,127],"techniques.":[35],"Despite":[36],"competitive":[37],"performance":[38],"previous":[40,108],"work,":[41],"the":[42,136,156,172,176,192],"full":[43,81],"approach":[45],"is":[46],"difficult":[47],"to":[48,50,58,107,135,165,171,183,191],"scale":[49],"large":[51],"corpora.":[53],"We":[54,103,159],"introduce":[55],"an":[56],"approximation":[57],"a":[59,66,125],"recent":[60],"model":[62,92,138],"that":[63,162],"still":[64],"has":[65],"clear":[67],"objective":[68],"function":[69],"but":[70],"improves":[71],"efficiency":[72],"by":[73,168],"using":[74],"hard":[75],"rather":[79],"than":[80,153],"inference.":[83],"Like":[84],"its":[85,148],"counterpart,":[87],"this":[88],"embedded":[89],"segmental":[90],"K-means":[91],"(ES-KMeans)":[93],"represents":[94],"arbitrary-length":[95],"word":[96,101,130],"segments":[97],"as":[98],"fixed-dimensional":[99],"acoustic":[100],"embeddings.":[102],"first":[104],"compare":[105],"ES-KMeans":[106,123,163],"on":[110],"common":[111],"English":[112],"Xitsonga":[114],"data":[115],"sets":[116],"(5":[117],"2.5":[119],"hours":[120],"speech):":[122],"outperforms":[124],"leading":[126],"method":[128],"segmentation,":[131],"giving":[132],"similar":[133],"scores":[134],"being":[140],"5":[141,173],"times":[142],"faster":[143],"fewer":[145],"hyperparameters.":[146],"However,":[147],"clusters":[149],"less":[151],"pure":[152],"those":[154],"other":[157],"models.":[158],"then":[160],"show":[161],"scales":[164],"larger":[166],"corpora":[167],"applying":[169],"it":[170,187],"languages":[174],"Zero":[177],"Resource":[178],"Speech":[179],"Challenge":[180],"2017":[181],"(up":[182],"45":[184],"hours),":[185],"where":[186],"performs":[188],"competitively":[189],"compared":[190],"challenge":[193],"baseline.":[194]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}