{"id":"https://openalex.org/W2161952424","doi":"https://doi.org/10.1162/089120101317066113","title":"A Statistical Model for Word Discovery in Transcribed Speech","display_name":"A Statistical Model for Word Discovery in Transcribed Speech","publication_year":2001,"publication_date":"2001-09-01","ids":{"openalex":"https://openalex.org/W2161952424","doi":"https://doi.org/10.1162/089120101317066113","mag":"2161952424"},"language":"en","primary_location":{"id":"doi:10.1162/089120101317066113","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120101317066113","pdf_url":"https://direct.mit.edu/coli/article-pdf/27/3/351/1797782/089120101317066113.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://direct.mit.edu/coli/article-pdf/27/3/351/1797782/089120101317066113.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046717231","display_name":"Anand Venkataraman","orcid":"https://orcid.org/0000-0001-6303-4820"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anand Venkataraman","raw_affiliation_strings":["STAR Lab, SRI International, 333 Ravenswood Ave., Menlo Park, CA 94025","STAR Lab, SRI International, 333 Ravenswood Ave., Menlo Park, CA 94025. E-mail:"],"affiliations":[{"raw_affiliation_string":"STAR Lab, SRI International, 333 Ravenswood Ave., Menlo Park, CA 94025","institution_ids":[]},{"raw_affiliation_string":"STAR Lab, SRI International, 333 Ravenswood Ave., Menlo Park, CA 94025. E-mail:","institution_ids":["https://openalex.org/I1298353152"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5046717231"],"corresponding_institution_ids":["https://openalex.org/I1298353152"],"apc_list":null,"apc_paid":null,"fwci":4.3643,"has_fulltext":false,"cited_by_count":111,"citation_normalized_percentile":{"value":0.94470298,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"27","issue":"3","first_page":"351","last_page":"372"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.993399977684021,"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/T12031","display_name":"Speech and dialogue systems","score":0.993399977684021,"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":0.8296838402748108},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6887269020080566},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6254155039787292},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5701373219490051},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.5361435413360596},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.4987609386444092},{"id":"https://openalex.org/keywords/statistical-learning","display_name":"Statistical learning","score":0.47392377257347107},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47078531980514526},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.46186381578445435},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08358976244926453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8296838402748108},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6887269020080566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6254155039787292},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5701373219490051},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.5361435413360596},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.4987609386444092},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.47392377257347107},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47078531980514526},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.46186381578445435},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08358976244926453},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1162/089120101317066113","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120101317066113","pdf_url":"https://direct.mit.edu/coli/article-pdf/27/3/351/1797782/089120101317066113.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.19.5103","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.19.5103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/J/J01/J01-3002.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.342.3550","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.342.3550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/cs/0111065v1.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.997.5603","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.997.5603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ensani.ir/storage/Files/20101126171848-404.pdf","raw_type":"text"},{"id":"pmh:oai:acl.sr.language-archives.org:J01-3002","is_oa":false,"landing_page_url":"http://www.aclweb.org/anthology/J01-3002","pdf_url":null,"source":{"id":"https://openalex.org/S4306402137","display_name":"The COCOON platform (University of Paris)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102197404","host_organization_name":"Universit\u00e9 Paris-Sud","host_organization_lineage":["https://openalex.org/I102197404"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:americanae.aecid.es:3673602","is_oa":false,"landing_page_url":"http://americanae.aecid.es/americanae/es/registros/registro.do?tipoRegistro=MTD&idBib=3673602","pdf_url":null,"source":{"id":"https://openalex.org/S4306400786","display_name":"Americanae (AECID Library)","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":""},{"id":"pmh:oai:doaj.org/article:a86c0651ae00450da1c7de249477bbcc","is_oa":true,"landing_page_url":"https://doaj.org/article/a86c0651ae00450da1c7de249477bbcc","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 27, Iss 3 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/089120101317066113","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120101317066113","pdf_url":"https://direct.mit.edu/coli/article-pdf/27/3/351/1797782/089120101317066113.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.550000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2161952424.pdf","grobid_xml":"https://content.openalex.org/works/W2161952424.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W76754543","https://openalex.org/W618881152","https://openalex.org/W1508165687","https://openalex.org/W1779834323","https://openalex.org/W1991133427","https://openalex.org/W1993768374","https://openalex.org/W1994022788","https://openalex.org/W1995991622","https://openalex.org/W2029948425","https://openalex.org/W2037752261","https://openalex.org/W2074546930","https://openalex.org/W2110485445","https://openalex.org/W2113641473","https://openalex.org/W2115867364","https://openalex.org/W2124973255","https://openalex.org/W2129287413","https://openalex.org/W2134237567","https://openalex.org/W2144800021","https://openalex.org/W2164770604","https://openalex.org/W2166391802","https://openalex.org/W2952343510","https://openalex.org/W4239549861"],"related_works":["https://openalex.org/W2172629291","https://openalex.org/W2380773642","https://openalex.org/W2384559435","https://openalex.org/W2337707338","https://openalex.org/W2393940967","https://openalex.org/W2159591557","https://openalex.org/W2785359773","https://openalex.org/W2058548953","https://openalex.org/W2385598138","https://openalex.org/W2366925922"],"abstract_inverted_index":{"A":[0],"statistical":[1],"model":[2,25],"for":[3,48],"segmentation":[4],"and":[5],"word":[6,20],"discovery":[7],"in":[8],"continuous":[9],"speech":[10],"is":[11,26,39],"presented.":[12],"An":[13],"incremental":[14],"unsupervised":[15],"learning":[16],"algorithm":[17,38],"to":[18],"infer":[19],"boundaries":[21],"based":[22],"on":[23],"this":[24],"described.":[27],"Results":[28],"are":[29],"also":[30],"presented":[31],"of":[32],"empirical":[33],"tests":[34],"showing":[35],"that":[36,44],"the":[37],"competitive":[40],"with":[41],"other":[42],"models":[43],"have":[45],"been":[46],"used":[47],"similar":[49],"tasks.":[50]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":9}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}