{"id":"https://openalex.org/W2089537772","doi":"https://doi.org/10.1109/icassp.2013.6639336","title":"Quantifying the value of pronunciation lexicons for keyword search in lowresource languages","display_name":"Quantifying the value of pronunciation lexicons for keyword search in lowresource languages","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2089537772","doi":"https://doi.org/10.1109/icassp.2013.6639336","mag":"2089537772"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639336","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639336","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5081371370","display_name":"Guoguo Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guoguo Chen","raw_affiliation_strings":["Center for Language and Speech Processing, and Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","Center for Language & Speech Process., Johns Hopkins Univ., Baltimore, MD, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, and Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language & Speech Process., Johns Hopkins Univ., Baltimore, MD, USA#TAB#","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Center for Language and Speech Processing, and Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","Center for Language & Speech Process., Johns Hopkins Univ., Baltimore, MD, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, and Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language & Speech Process., Johns Hopkins Univ., Baltimore, MD, USA#TAB#","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["Center for Language and Speech Processing, and Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","Center for Language & Speech Process., Johns Hopkins Univ., Baltimore, MD, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, and Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language & Speech Process., Johns Hopkins Univ., Baltimore, MD, USA#TAB#","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017882589","display_name":"Jan Trmal","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jan Trmal","raw_affiliation_strings":["Center for Language and Speech Processing, and Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","Center for Language & Speech Process., Johns Hopkins Univ., Baltimore, MD, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, and Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language & Speech Process., Johns Hopkins Univ., Baltimore, MD, USA#TAB#","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015876016","display_name":"David Yarowsky","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Yarowsky","raw_affiliation_strings":["Center for Language and Speech Processing, and Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","Center for Language & Speech Process., Johns Hopkins Univ., Baltimore, MD, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, and Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language & Speech Process., Johns Hopkins Univ., Baltimore, MD, USA#TAB#","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100840874","display_name":"Oguz Yilmaz","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oguz Yilmaz","raw_affiliation_strings":["Center for Language and Speech Processing, and Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","Center for Language & Speech Process., Johns Hopkins Univ., Baltimore, MD, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, and Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language & Speech Process., Johns Hopkins Univ., Baltimore, MD, USA#TAB#","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8560","last_page":"8564"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9976000189781189,"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":0.877203106880188},{"id":"https://openalex.org/keywords/tagalog","display_name":"Tagalog","score":0.8215904235839844},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7488768696784973},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.6395347118377686},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6102615594863892},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5382480621337891},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5225600600242615},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4961877465248108},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4693537652492523},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.4596535563468933},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1466076672077179}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.877203106880188},{"id":"https://openalex.org/C2779388314","wikidata":"https://www.wikidata.org/wiki/Q34057","display_name":"Tagalog","level":2,"score":0.8215904235839844},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7488768696784973},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6395347118377686},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6102615594863892},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5382480621337891},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5225600600242615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4961877465248108},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4693537652492523},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.4596535563468933},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1466076672077179},{"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:10.1109/icassp.2013.6639336","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639336","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.674.401","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.674.401","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.clsp.jhu.edu/%7Eguoguo/papers/icassp2013_lexicon_value.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":21,"referenced_works":["https://openalex.org/W44395966","https://openalex.org/W82886505","https://openalex.org/W114193738","https://openalex.org/W1506212051","https://openalex.org/W1524333225","https://openalex.org/W1534448508","https://openalex.org/W1553630706","https://openalex.org/W1555037511","https://openalex.org/W1582482241","https://openalex.org/W1631260214","https://openalex.org/W1654858490","https://openalex.org/W2056786202","https://openalex.org/W2090755665","https://openalex.org/W2132991150","https://openalex.org/W2139698650","https://openalex.org/W2167338739","https://openalex.org/W3146209407","https://openalex.org/W6601801988","https://openalex.org/W6631362777","https://openalex.org/W6633142163","https://openalex.org/W6636811518"],"related_works":["https://openalex.org/W171544630","https://openalex.org/W2468068997","https://openalex.org/W3212836698","https://openalex.org/W4240433226","https://openalex.org/W2128446822","https://openalex.org/W2315343956","https://openalex.org/W4237692438","https://openalex.org/W611807403","https://openalex.org/W2336826924","https://openalex.org/W1560348878"],"abstract_inverted_index":{"This":[0],"paper":[1],"quantifies":[2],"the":[3,39,63,85,104,108,135,155],"value":[4,92],"of":[5,53,126,138],"pronunciation":[6],"lexicons":[7,106],"in":[8,21,36,81,88,129,144,154],"large":[9,55],"vocabulary":[10],"continuous":[11],"speech":[12,35,113],"recognition":[13],"(LVCSR)":[14],"systems":[15,29],"that":[16,49,61,102],"support":[17],"keyword":[18],"search":[19],"(KWS)":[20],"low":[22],"resource":[23],"languages.":[24],"State-of-the-art":[25],"LVCSR":[26,109,156],"and":[27,38,148],"KWS":[28,143],"are":[30,93],"developed":[31],"for":[32,122,142,150],"conversational":[33],"telephone":[34],"Tagalog,":[37],"baseline":[40],"lexicon":[41,140],"is":[42,59,99,114],"augmented":[43,105],"via":[44],"three":[45],"different":[46],"grapheme-to-phoneme":[47],"models":[48],"yield":[50],"increasing":[51],"coverage":[52,66],"a":[54],"Tagalog":[56],"word-list.":[57],"It":[58,98],"demonstrated":[60],"while":[62],"increased":[64],"lexical":[65],"-":[67,73],"or":[68],"reduced":[69],"out-of-vocabulary":[70],"(OOV)":[71],"rate":[72],"leads":[74],"to":[75,116],"only":[76],"modest":[77],"(ca":[78],"1%-4%)":[79],"improvements":[80,87],"word":[82],"error":[83],"rate,":[84],"concomitant":[86],"actual":[89],"term":[90],"weighted":[91],"as":[94,96],"much":[95],"60%.":[97],"also":[100],"shown":[101],"incorporating":[103],"into":[107],"system":[110],"before":[111],"indexing":[112],"superior":[115],"using":[117,151],"them":[118,152],"post":[119],"facto,":[120],"e.g.,":[121],"approximate":[123],"phonetic":[124],"matching":[125],"OOV":[127],"keywords":[128],"pre-indexed":[130],"lattices.":[131],"These":[132],"results":[133],"underscore":[134],"disproportionate":[136],"importance":[137],"automatic":[139],"augmentation":[141],"morphologically":[145],"rich":[146],"languages,":[147],"advocate":[149],"early":[153],"stage.":[157]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}