{"id":"https://openalex.org/W4408352368","doi":"https://doi.org/10.1109/icassp49660.2025.10890719","title":"Unsupervised Word Discovery: Boundary Detection with Clustering vs. Dynamic Programming","display_name":"Unsupervised Word Discovery: Boundary Detection with Clustering vs. Dynamic Programming","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352368","doi":"https://doi.org/10.1109/icassp49660.2025.10890719"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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":null,"display_name":"Simon Malan","orcid":null},"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":true,"raw_author_name":"Simon Malan","raw_affiliation_strings":["Stellenbosch University,Electrical and Electronic Engineering,South Africa"],"affiliations":[{"raw_affiliation_string":"Stellenbosch University,Electrical and Electronic Engineering,South Africa","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046382731","display_name":"Benjamin van Niekerk","orcid":"https://orcid.org/0000-0001-9207-6309"},"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":"Benjamin van Niekerk","raw_affiliation_strings":["Stellenbosch University,Electrical and Electronic Engineering,South Africa"],"affiliations":[{"raw_affiliation_string":"Stellenbosch University,Electrical and Electronic Engineering,South Africa","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"last","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":["Stellenbosch University,Electrical and Electronic Engineering,South Africa"],"affiliations":[{"raw_affiliation_string":"Stellenbosch University,Electrical and Electronic Engineering,South Africa","institution_ids":["https://openalex.org/I26092322"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I26092322"],"apc_list":null,"apc_paid":null,"fwci":2.2283,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87697758,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"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/T10820","display_name":"Fuzzy Logic and Control Systems","score":0.8174999952316284,"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/T10820","display_name":"Fuzzy Logic and Control Systems","score":0.8174999952316284,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.7642999887466431,"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":0.739300012588501,"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":0.7931070327758789},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.677821695804596},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.56839519739151},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5238654017448425},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5229190587997437},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.48295825719833374},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.4549415409564972},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40676945447921753},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3409530818462372},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1463666558265686},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10210973024368286}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7931070327758789},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.677821695804596},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.56839519739151},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5238654017448425},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5229190587997437},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.48295825719833374},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.4549415409564972},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40676945447921753},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3409530818462372},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1463666558265686},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10210973024368286},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W130754613","https://openalex.org/W1494198834","https://openalex.org/W1778492285","https://openalex.org/W1997505733","https://openalex.org/W2010188467","https://openalex.org/W2025482506","https://openalex.org/W2059652594","https://openalex.org/W2063303346","https://openalex.org/W2091746061","https://openalex.org/W2114347655","https://openalex.org/W2398490608","https://openalex.org/W2418471937","https://openalex.org/W2468716020","https://openalex.org/W2483390977","https://openalex.org/W2802557066","https://openalex.org/W2964169922","https://openalex.org/W3093096176","https://openalex.org/W3198782837","https://openalex.org/W3209059054","https://openalex.org/W3209993061","https://openalex.org/W3210530853","https://openalex.org/W4224875474","https://openalex.org/W4296710617","https://openalex.org/W4313053756","https://openalex.org/W4313182775","https://openalex.org/W4372346125","https://openalex.org/W4375869060","https://openalex.org/W4394773771","https://openalex.org/W4402112143","https://openalex.org/W4402112189","https://openalex.org/W6691362072","https://openalex.org/W6861041784"],"related_works":["https://openalex.org/W4298130764","https://openalex.org/W2804364458","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2090259340","https://openalex.org/W1926736923","https://openalex.org/W2158836806","https://openalex.org/W2393816671","https://openalex.org/W2083665254","https://openalex.org/W2942177010"],"abstract_inverted_index":{"We":[0],"look":[1],"at":[2],"the":[3,47,56,69,82,95],"long-standing":[4],"problem":[5],"of":[6],"segmenting":[7],"unlabeled":[8],"speech":[9],"into":[10,16],"word-like":[11],"segments":[12,58],"and":[13,78],"clustering":[14],"these":[15],"a":[17,23,38,61,64],"lexicon.":[18,62],"Several":[19],"previous":[20],"methods":[21],"use":[22],"scoring":[24],"model":[25],"coupled":[26],"with":[27,75],"dynamic":[28,72],"programming":[29,73],"to":[30,59,94],"find":[31],"an":[32],"optimal":[33],"segmentation.":[34],"Here":[35],"we":[36,42,54,67],"propose":[37],"much":[39],"simpler":[40],"strategy:":[41],"predict":[43],"word":[44],"boundaries":[45],"using":[46],"dissimilarity":[48],"between":[49],"adjacent":[50],"self-supervised":[51],"features,":[52],"then":[53],"cluster":[55],"predicted":[57],"construct":[60],"For":[63],"fair":[65],"comparison,":[66],"update":[68],"older":[70],"ES-KMeans":[71],"method":[74],"better":[76],"features":[77],"boundary":[79],"constraints.":[80],"On":[81],"five-language":[83],"ZeroSpeech":[84],"benchmarks,":[85],"our":[86],"simple":[87],"approach":[88],"gives":[89],"similar":[90],"state-of-the-art":[91],"results":[92],"compared":[93],"new":[96],"ES-KMeans+":[97],"method,":[98],"while":[99],"being":[100],"almost":[101],"five":[102],"times":[103],"faster.":[104],"Project":[105],"webpage:":[106],"https://s-malan.github.io/prom-seg-clus.":[107]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
