{"id":"https://openalex.org/W2964076070","doi":"https://doi.org/10.21437/eurospeech.2003-110","title":"Techniques for effective vocabulary selection","display_name":"Techniques for effective vocabulary selection","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W2964076070","doi":"https://doi.org/10.21437/eurospeech.2003-110","mag":"2964076070"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-110","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-110","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","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/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":false,"raw_author_name":"Anand Venkataraman","raw_affiliation_strings":["SRI-International"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI-International","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100396375","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0002-0356-1968"},"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":false,"raw_author_name":"Wen Wang","raw_affiliation_strings":["SRI-International"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI-International","institution_ids":["https://openalex.org/I1298353152"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1298353152"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"245","last_page":"248"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9997000098228455,"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":0.9988999962806702,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.9276069402694702},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7918593883514404},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.711452066898346},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5868648290634155},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5650409460067749},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4903736114501953},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.487621933221817},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4518933594226837},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13614878058433533},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10433784127235413}],"concepts":[{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.9276069402694702},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7918593883514404},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.711452066898346},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5868648290634155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5650409460067749},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4903736114501953},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.487621933221817},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4518933594226837},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13614878058433533},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10433784127235413},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.2003-110","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-110","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1618325928","https://openalex.org/W1631260214","https://openalex.org/W1965555277","https://openalex.org/W2006681603","https://openalex.org/W2049633694","https://openalex.org/W2113641473","https://openalex.org/W2316904474","https://openalex.org/W3146209407"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2101155126","https://openalex.org/W2043093291","https://openalex.org/W2363545964"],"abstract_inverted_index":{"The":[0],"vocabulary":[1,29,44,68],"of":[2,61],"a":[3,10,31],"continuous":[4],"speech":[5],"recognition":[6],"(CSR)":[7],"system":[8],"is":[9],"significant":[11],"factor":[12],"in":[13,58],"determining":[14],"its":[15],"performance.":[16],"In":[17],"this":[18],"paper,":[19],"we":[20],"present":[21],"three":[22],"principled":[23],"approaches":[24,49],"to":[25],"select":[26],"the":[27,38,59],"target":[28,39],"for":[30,70],"particular":[32],"domain":[33],"by":[34],"trading":[35],"off":[36],"between":[37],"out-of-vocabulary":[40],"(OOV)":[41],"rate":[42,63],"and":[43],"size.":[45],"We":[46],"evaluate":[47],"these":[48],"against":[50,66],"an":[51],"ad-hoc":[52],"baseline":[53],"strategy.":[54],"Results":[55],"are":[56],"presented":[57],"form":[60],"OOV":[62],"graphs":[64],"plotted":[65],"increasing":[67],"size":[69],"each":[71],"technique.":[72]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
