{"id":"https://openalex.org/W2166936558","doi":"https://doi.org/10.1109/icassp.2005.1415111","title":"Optimal Subset Selection from Text Databases","display_name":"Optimal Subset Selection from Text Databases","publication_year":2006,"publication_date":"2006-10-11","ids":{"openalex":"https://openalex.org/W2166936558","doi":"https://doi.org/10.1109/icassp.2005.1415111","mag":"2166936558"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2005.1415111","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"},"type":"conference-paper","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":false,"raw_author_name":"Jilei Tian","raw_affiliation_strings":["Multimedia Technologies Laboratory, Nokia Research Center, Tampere, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Technologies Laboratory, Nokia Research Center, Tampere, Finland","institution_ids":["https://openalex.org/I2738502077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042260991","display_name":"Jukka K. Nurminen","orcid":"https://orcid.org/0000-0001-5083-1927"},"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":"J. Nurminen","raw_affiliation_strings":["Multimedia Technologies Laboratory, Nokia Research Center, Tampere, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Technologies Laboratory, Nokia Research Center, Tampere, Finland","institution_ids":["https://openalex.org/I2738502077"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040670032","display_name":"Imre Kiss","orcid":"https://orcid.org/0000-0001-5373-7485"},"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":"I. Kiss","raw_affiliation_strings":["Multimedia Technologies Laboratory, Nokia Research Center, Tampere, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Technologies Laboratory, Nokia Research Center, Tampere, Finland","institution_ids":["https://openalex.org/I2738502077"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2738502077"],"apc_list":null,"apc_paid":null,"fwci":1.2214,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.79938404,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"305","last_page":"308"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9957000017166138,"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":0.9957000017166138,"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":0.9922000169754028,"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/T10320","display_name":"Neural Networks and Applications","score":0.9907000064849854,"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":0.8540867567062378},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.7441378831863403},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5795688629150391},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5772163271903992},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5689210891723633},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5538851618766785},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5517749190330505},{"id":"https://openalex.org/keywords/syllabification","display_name":"Syllabification","score":0.508040189743042},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4979386329650879},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.45809608697891235},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4276292026042938},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40697798132896423},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.0847950279712677},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0780666172504425}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8540867567062378},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.7441378831863403},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5795688629150391},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5772163271903992},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5689210891723633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5538851618766785},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5517749190330505},{"id":"https://openalex.org/C2779211743","wikidata":"https://www.wikidata.org/wiki/Q11994045","display_name":"Syllabification","level":3,"score":0.508040189743042},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4979386329650879},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45809608697891235},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4276292026042938},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40697798132896423},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.0847950279712677},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0780666172504425},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2005.1415111","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W34978987","https://openalex.org/W131188140","https://openalex.org/W182267589","https://openalex.org/W1499275966","https://openalex.org/W1554663460","https://openalex.org/W1911232923","https://openalex.org/W2102443632","https://openalex.org/W2110442145","https://openalex.org/W4388297464","https://openalex.org/W6601435658","https://openalex.org/W6605238854","https://openalex.org/W6607389590"],"related_works":["https://openalex.org/W3139922418","https://openalex.org/W1966233298","https://openalex.org/W3127730864","https://openalex.org/W1590229542","https://openalex.org/W2165592219","https://openalex.org/W4301674895","https://openalex.org/W2962695106","https://openalex.org/W4287644835","https://openalex.org/W3092281475","https://openalex.org/W3098003361"],"abstract_inverted_index":{"Speech":[0],"and":[1,16],"language":[2,14,128],"processing":[3,129],"techniques,":[4],"such":[5],"as":[6],"automatic":[7,87],"speech":[8],"recognition":[9],"(ASR),":[10],"text-to-speech":[11],"(TTS)":[12],"synthesis,":[13],"understanding":[15],"translation,":[17],"will":[18],"play":[19],"a":[20,42,124],"key":[21],"role":[22],"in":[23,73,85,108,123],"tomorrow's":[24],"user":[25],"interfaces.":[26],"Many":[27],"of":[28,54,78,103,113,127],"these":[29],"techniques":[30],"employ":[31],"models":[32],"that":[33,64,94,131],"must":[34],"be":[35,121],"trained":[36,115],"using":[37,60],"text":[38,50,135],"data.":[39],"We":[40],"introduce":[41],"novel":[43],"method":[44],"for":[45],"training":[46,56,105,133],"set":[47],"selection":[48,81,98],"from":[49],"databases.":[51,136],"The":[52,76,90,117],"quality":[53,102,112],"the":[55,67,71,74,79,95,101,104,111,114],"subset":[57,80],"is":[58,83],"ensured":[59],"an":[61,86],"objective":[62],"function":[63],"effectively":[65],"describes":[66],"coverage":[68],"achieved":[69],"with":[70,134],"strings":[72],"subset.":[75],"validity":[77],"technique":[82],"verified":[84],"syllabification":[88],"task.":[89],"results":[91],"clearly":[92],"indicate":[93],"proposed":[96],"systematic":[97],"approach":[99],"maximizes":[100],"set,":[106],"which":[107],"turn":[109],"improves":[110],"model.":[116],"presented":[118],"idea":[119],"can":[120],"used":[122],"wide":[125],"variety":[126],"applications":[130],"require":[132]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}