{"id":"https://openalex.org/W2140499244","doi":"https://doi.org/10.1109/icassp.2009.4960572","title":"Optimization of text database using hierachical clustering","display_name":"Optimization of text database using hierachical clustering","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2140499244","doi":"https://doi.org/10.1109/icassp.2009.4960572","mag":"2140499244"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960572","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960572","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 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/A5103093321","display_name":"Jilei Tian","orcid":"https://orcid.org/0000-0002-4588-9398"},"institutions":[{"id":"https://openalex.org/I2738502077","display_name":"Nokia (Finland)","ror":"https://ror.org/04pkc8m17","country_code":"FI","type":"company","lineage":["https://openalex.org/I2738502077"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Jilei Tian","raw_affiliation_strings":["Nokia Research Center, Tampere, Finland","Media Laboratory, Nokia Research Center, Tampere, Finland#TAB#"],"affiliations":[{"raw_affiliation_string":"Nokia Research Center, Tampere, Finland","institution_ids":["https://openalex.org/I2738502077"]},{"raw_affiliation_string":"Media Laboratory, Nokia Research Center, Tampere, Finland#TAB#","institution_ids":["https://openalex.org/I2738502077"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112039585","display_name":"Jani Nurminen","orcid":null},"institutions":[{"id":"https://openalex.org/I2738502077","display_name":"Nokia (Finland)","ror":"https://ror.org/04pkc8m17","country_code":"FI","type":"company","lineage":["https://openalex.org/I2738502077"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jani Nurminen","raw_affiliation_strings":["Nokia Devices Research And Development, Tampere, Finland","Nokia Devices R&D, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Nokia Devices Research And Development, Tampere, Finland","institution_ids":["https://openalex.org/I2738502077"]},{"raw_affiliation_string":"Nokia Devices R&D, Tampere, Finland","institution_ids":["https://openalex.org/I2738502077"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103093321"],"corresponding_institution_ids":["https://openalex.org/I2738502077"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.138343,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4269","last_page":"4272"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9959999918937683,"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":0.9959999918937683,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9955999851226807,"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":0.8186352849006653},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7025085091590881},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.526612401008606},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5225141048431396},{"id":"https://openalex.org/keywords/levenshtein-distance","display_name":"Levenshtein distance","score":0.49375733733177185},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.47740569710731506},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4607447385787964},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4547426700592041},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4457484185695648},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42960065603256226},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4191797971725464},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.16409558057785034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8186352849006653},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7025085091590881},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.526612401008606},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5225141048431396},{"id":"https://openalex.org/C2777515626","wikidata":"https://www.wikidata.org/wiki/Q496939","display_name":"Levenshtein distance","level":2,"score":0.49375733733177185},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.47740569710731506},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4607447385787964},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4547426700592041},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4457484185695648},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42960065603256226},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4191797971725464},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.16409558057785034},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp.2009.4960572","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960572","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1012.2145","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1012.2145","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/Jilei_Tian/publication/220735726_Optimization_of_text_database_using_hierachical_clustering/links/02e7e5295644a5b0a1000000.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1012.8358","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1012.8358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mirlab.org/conference_papers/International_Conference/ICASSP%202009/pdfs/0004269.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1018.9735","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1018.9735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.emime.org/learn/publications/papers/Jilei-ICASSP2009.pdf/at_download/file/","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1025.1660","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1025.1660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/Jilei_Tian/publication/220735726_Optimization_of_text_database_using_hierachical_clustering/links/02e7e5295644a5b0a1000000.pdf?origin%3Dpublication_detail","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W34978987","https://openalex.org/W131188140","https://openalex.org/W182267589","https://openalex.org/W1554663460","https://openalex.org/W1911232923","https://openalex.org/W2102443632","https://openalex.org/W2166936558","https://openalex.org/W4388297464","https://openalex.org/W6601435658","https://openalex.org/W6605238854","https://openalex.org/W6607389590"],"related_works":["https://openalex.org/W2575897682","https://openalex.org/W2081797125","https://openalex.org/W2996079066","https://openalex.org/W1967312449","https://openalex.org/W1986094003","https://openalex.org/W3200375535","https://openalex.org/W2953038320","https://openalex.org/W2092793748","https://openalex.org/W4299394613","https://openalex.org/W4211231063"],"abstract_inverted_index":{"Many":[0],"speech":[1],"and":[2,43,109],"language":[3,126],"related":[4],"techniques":[5],"employ":[6],"models":[7],"that":[8,67,129],"are":[9],"trained":[10,84],"using":[11,40],"text":[12,28,133],"data.":[13,134],"In":[14],"this":[15],"paper,":[16],"we":[17],"introduce":[18],"a":[19,59,122],"novel":[20],"method":[21],"for":[22,36],"selecting":[23],"optimized":[24,39],"training":[25,37,74,131],"sets":[26],"from":[27],"databases.":[29],"The":[30,48,63,115],"coverage":[31],"of":[32,50,82,102,125],"the":[33,44,51,68,73,80,83,88,94,100,106],"subset":[34,53],"selected":[35],"is":[38,56],"hierarchical":[41,96],"clustering":[42,97],"generalized":[45],"Levenshtein":[46],"distance.":[47],"validity":[49],"proposed":[52,69,95],"optimization":[54],"technique":[55],"verified":[57],"in":[58,77,121],"data-driven":[60],"syllabification":[61],"task.":[62],"results":[64],"clearly":[65],"indicate":[66],"approach":[70,98],"meaningfully":[71],"optimizes":[72],"set,":[75],"which":[76],"turn":[78],"improves":[79,99],"quality":[81],"model.":[85],"Compared":[86],"to":[87],"existing":[89],"state-of-the-art":[90],"data":[91,103,111],"selection":[92,113],"technique,":[93],"compactness":[101],"clusters,":[104],"decreases":[105],"computational":[107],"complexity":[108],"makes":[110],"set":[112],"scalable.":[114],"presented":[116],"idea":[117],"can":[118],"be":[119],"used":[120],"wide":[123],"variety":[124],"processing":[127],"applications":[128],"require":[130],"with":[132]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}