{"id":"https://openalex.org/W2121997342","doi":"https://doi.org/10.1109/icassp.2008.4518528","title":"Unsupervised optimal phoneme segmentation: Objectives, algorithm and comparisons","display_name":"Unsupervised optimal phoneme segmentation: Objectives, algorithm and comparisons","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2121997342","doi":"https://doi.org/10.1109/icassp.2008.4518528","mag":"2121997342"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518528","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","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":"https://openalex.org/A5100748135","display_name":"Yu Qiao","orcid":"https://orcid.org/0000-0002-1889-2567"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yu Qiao","raw_affiliation_strings":["Graduate School of Frontier Sciences, University of Tokyo, Japan","Grad. Sch. of Frontier Sci., Tokyo Univ., Tokyo"],"affiliations":[{"raw_affiliation_string":"Graduate School of Frontier Sciences, University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Grad. Sch. of Frontier Sci., Tokyo Univ., Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066330649","display_name":"Naoya Shimomura","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoya Shimomura","raw_affiliation_strings":["Graduate School of Frontier Sciences, University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Frontier Sciences, University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041213266","display_name":"Nobuaki Minematsu","orcid":"https://orcid.org/0000-0002-8778-9555"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobuaki Minematsu","raw_affiliation_strings":["Graduate School of Frontier Sciences, University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Frontier Sciences, University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100748135"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":4.8097,"has_fulltext":false,"cited_by_count":77,"citation_normalized_percentile":{"value":0.96897375,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3989","last_page":"3992"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9987999796867371,"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/segmentation","display_name":"Segmentation","score":0.7231878638267517},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6947457790374756},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.658156156539917},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.6082980036735535},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5279107689857483},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5083653330802917},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49464985728263855},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4803920388221741},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.47446876764297485},{"id":"https://openalex.org/keywords/minimum-description-length","display_name":"Minimum description length","score":0.44008946418762207},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.24621567130088806}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7231878638267517},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6947457790374756},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.658156156539917},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6082980036735535},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5279107689857483},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5083653330802917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49464985728263855},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4803920388221741},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.47446876764297485},{"id":"https://openalex.org/C87465248","wikidata":"https://www.wikidata.org/wiki/Q1417790","display_name":"Minimum description length","level":2,"score":0.44008946418762207},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.24621567130088806},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2008.4518528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518528","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","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":22,"referenced_works":["https://openalex.org/W1589615572","https://openalex.org/W1950396994","https://openalex.org/W1971784203","https://openalex.org/W1982475475","https://openalex.org/W2054665642","https://openalex.org/W2083904075","https://openalex.org/W2098363562","https://openalex.org/W2099111195","https://openalex.org/W2106596127","https://openalex.org/W2115606020","https://openalex.org/W2152486668","https://openalex.org/W2164931791","https://openalex.org/W2171752983","https://openalex.org/W2319660501","https://openalex.org/W2339940010","https://openalex.org/W2478708596","https://openalex.org/W2479250278","https://openalex.org/W2907162034","https://openalex.org/W3140237324","https://openalex.org/W4299681030","https://openalex.org/W6635066055","https://openalex.org/W6684765037"],"related_works":["https://openalex.org/W80423236","https://openalex.org/W4298831272","https://openalex.org/W2962916388","https://openalex.org/W2086694237","https://openalex.org/W2095614499","https://openalex.org/W2489956408","https://openalex.org/W3164669818","https://openalex.org/W349256592","https://openalex.org/W4213307346","https://openalex.org/W1573546415"],"abstract_inverted_index":{"Phoneme":[0],"segmentation":[1,15,46,156],"is":[2,35,37,80],"a":[3,28,49,98],"fundamental":[4],"problem":[5,47],"in":[6],"many":[7],"speech":[8],"recognition":[9],"and":[10,22,25,54,73,87,146],"synthesis":[11],"studies.":[12],"Unsupervised":[13],"phoneme":[14],"assumes":[16],"no":[17],"knowledge":[18],"on":[19,126],"linguistic":[20],"contents":[21],"acoustic":[23],"models,":[24],"thus":[26],"poses":[27],"challenging":[29],"problem.":[30],"The":[31,136],"essential":[32],"question":[33],"here":[34],"what":[36],"the":[38,44,105,116,131,143,152],"optimal":[39,45,106],"segmentation.":[40],"This":[41],"paper":[42],"formulates":[43],"into":[48],"probabilistic":[50],"framework.":[51],"Using":[52],"statistics":[53],"information":[55,83],"theory":[56,86],"analysis,":[57],"we":[58],"develop":[59],"three":[60,133],"different":[61],"objective":[62,134],"functions,":[63],"namely,":[64],"summation":[65],"of":[66],"square":[67],"error":[68],"(SSE),":[69],"log":[70],"determinant":[71],"(LD)":[72],"rate":[74,84,140],"distortion":[75,85,141],"(RD).":[76],"Specially,":[77],"RD":[78],"function":[79],"derived":[81],"from":[82],"can":[88],"be":[89],"related":[90],"to":[91,103,114,129],"human":[92],"signal":[93],"perception":[94],"mechanism.":[95],"We":[96,108,122],"introduce":[97],"time-constrained":[99],"agglomerative":[100],"clustering":[101],"algorithm":[102,117],"find":[104],"segmentations.":[107],"also":[109],"propose":[110],"an":[111],"efficient":[112],"method":[113,150],"implement":[115],"by":[118],"using":[119],"integration":[120],"functions.":[121,135],"carry":[123],"out":[124],"experiments":[125],"TIMIT":[127],"database":[128],"compare":[130],"above":[132],"results":[137],"show":[138],"that":[139,148],"achieves":[142],"best":[144],"performance":[145],"indicate":[147],"our":[149],"outperforms":[151],"recently":[153],"published":[154],"unsupervised":[155],"methods.":[157]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}