{"id":"https://openalex.org/W135240325","doi":"https://doi.org/10.21437/eurospeech.2003-159","title":"Using untranscribed user utterances for improving language models based on confidence scoring","display_name":"Using untranscribed user utterances for improving language models based on confidence scoring","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W135240325","doi":"https://doi.org/10.21437/eurospeech.2003-159","mag":"135240325"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-159","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-159","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/A5085401834","display_name":"Mikio Nakano","orcid":"https://orcid.org/0000-0001-6057-3132"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mikio Nakano","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5114018312","display_name":"Timothy J. Hazen","orcid":"https://orcid.org/0009-0006-1413-9590"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Timothy J. Hazen","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"417","last_page":"420"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":1.0,"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/T12031","display_name":"Speech and dialogue systems","score":1.0,"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/T10028","display_name":"Topic Modeling","score":0.9988999962806702,"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":0.9987999796867371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8582113981246948},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6714997887611389},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6600396633148193},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6326543688774109},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5578967928886414},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5514942407608032},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12600558996200562}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8582113981246948},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6714997887611389},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6600396633148193},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6326543688774109},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5578967928886414},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5514942407608032},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12600558996200562},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/eurospeech.2003-159","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-159","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.378.803","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.378.803","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://people.csail.mit.edu/hazen/publications/Eurospeech03_Nakano.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8500000238418579,"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":7,"referenced_works":["https://openalex.org/W1601764844","https://openalex.org/W1680913401","https://openalex.org/W1877154798","https://openalex.org/W2100271913","https://openalex.org/W2109933326","https://openalex.org/W2130607791","https://openalex.org/W2161482971"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2621258238","https://openalex.org/W2382781231","https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4306742369","https://openalex.org/W3204019825","https://openalex.org/W2028097510","https://openalex.org/W2505877856","https://openalex.org/W2118730790"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,22,28],"method":[4],"for":[5,17,39],"reducing":[6,106],"the":[7,78,89,94,107],"effort":[8,108],"of":[9,25,31,83,88],"transcribing":[10],"user":[11,91],"utterances":[12,33,41,63,92],"to":[13,45,57,71,76],"develop":[14],"language":[15,59,79],"models":[16],"conversational":[18],"speech":[19],"recognition":[20,37,103],"when":[21],"small":[23],"number":[24,30],"transcribed":[26,74],"and":[27],"large":[29],"untranscribed":[32,40,90],"are":[34,42,55,97],"available.":[35],"The":[36,62,81],"hypotheses":[38,51],"classified":[43],"according":[44],"their":[46],"confidence":[47,54,67],"scores":[48],"such":[49],"that":[50,64],"with":[52],"high":[53],"used":[56],"enhance":[58],"model":[60],"training.":[61],"receive":[65],"low":[66],"can":[68],"be":[69,72],"scheduled":[70],"manually":[73],"first":[75],"improve":[77],"model.":[80],"results":[82],"experiments":[84],"using":[85],"automatic":[86],"transcription":[87],"show":[93],"proposed":[95],"methods":[96],"effective":[98],"in":[99,102],"achieving":[100],"improvements":[101],"accuracy":[104],"while":[105],"required":[109],"from":[110],"manual":[111],"transcription.":[112],"1.":[113]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}