{"id":"https://openalex.org/W2000654171","doi":"https://doi.org/10.1109/asru.2013.6707766","title":"Using proxies for OOV keywords in the keyword search task","display_name":"Using proxies for OOV keywords in the keyword search task","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W2000654171","doi":"https://doi.org/10.1109/asru.2013.6707766","mag":"2000654171"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2013.6707766","doi":"https://doi.org/10.1109/asru.2013.6707766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707766","pdf_url":null,"source":{"id":"https://openalex.org/S7407088663","display_name":"IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W2000654171"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"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,"observed_orcids":[]},"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, The Johns Hopkins University, Baltimore, MD, USA","Center for Language & Speech Process. & Human Language Technol. Center of Excellence, Johns Hopkins Univ., Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language & Speech Process. & Human Language Technol. Center of Excellence, Johns Hopkins Univ., Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100840874","display_name":"Oguz Yilmaz","orcid":"https://orcid.org/0000-0003-1884-0246","observed_orcids":["https://orcid.org/0000-0003-1884-0246"]},"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, The Johns Hopkins University, Baltimore, MD, USA","Center for Language & Speech Process. & Human Language Technol. Center of Excellence, Johns Hopkins Univ., Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language & Speech Process. & Human Language Technol. Center of Excellence, Johns Hopkins Univ., Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017882589","display_name":"Jan Trmal","orcid":null,"observed_orcids":[]},"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, The Johns Hopkins University, Baltimore, MD, USA","Center for Language & Speech Process. & Human Language Technol. Center of Excellence, Johns Hopkins Univ., Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language & Speech Process. & Human Language Technol. Center of Excellence, Johns Hopkins Univ., Baltimore, MD, USA","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","observed_orcids":["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, The Johns Hopkins University, Baltimore, MD, USA","Center for Language & Speech Process. & Human Language Technol. Center of Excellence, Johns Hopkins Univ., Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language & Speech Process. & Human Language Technol. Center of Excellence, Johns Hopkins Univ., Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev P. Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897","observed_orcids":["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, The Johns Hopkins University, Baltimore, MD, USA","Center for Language & Speech Process. & Human Language Technol. Center of Excellence, Johns Hopkins Univ., Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language & Speech Process. & Human Language Technol. Center of Excellence, Johns Hopkins Univ., Baltimore, MD, USA","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":7.7611,"has_fulltext":false,"cited_by_count":96,"citation_normalized_percentile":{"value":0.9837733,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"416","last_page":"421"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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/T10860","display_name":"Speech and Audio Processing","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/keyword-search","display_name":"keyword search","score":0.9380000233650208},{"id":"https://openalex.org/keywords/weighted-finite-state-transducers","display_name":"weighted finite-state transducers","score":0.8529999852180481},{"id":"https://openalex.org/keywords/speech-search","display_name":"speech search","score":0.7599999904632568},{"id":"https://openalex.org/keywords/tagalog","display_name":"Tagalog","score":0.8339999914169312},{"id":"https://openalex.org/keywords/word-lattices","display_name":"word lattices","score":0.7400000095367432},{"id":"https://openalex.org/keywords/pronunciation-dictionary","display_name":"pronunciation dictionary","score":0.8529999852180481},{"id":"https://openalex.org/keywords/grapheme-to-phoneme-conversion","display_name":"grapheme-to-phoneme conversion","score":0.9169999957084656},{"id":"https://openalex.org/keywords/word-index","display_name":"word index","score":0.6439999938011169},{"id":"https://openalex.org/keywords/large-vocabulary-continuous-speech-recognition","display_name":"large vocabulary continuous speech recognition","score":0.800000011920929}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.864915668964386},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6939746737480164},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.675407350063324},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6174808740615845},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6033620834350586},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5808917284011841},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.575513482093811},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.5379372835159302},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.535747230052948},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5333777666091919},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5278052091598511},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.4933132231235504},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.48991721868515015},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.42123186588287354},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0776662826538086},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","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/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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru.2013.6707766","doi":"https://doi.org/10.1109/asru.2013.6707766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707766","pdf_url":null,"source":{"id":"https://openalex.org/S7407088663","display_name":"IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.676.4085","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.676.4085","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/asru2013_proxy_keyword.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W32347851","https://openalex.org/W49437105","https://openalex.org/W114193738","https://openalex.org/W183136171","https://openalex.org/W1524333225","https://openalex.org/W1582482241","https://openalex.org/W1631260214","https://openalex.org/W1983927863","https://openalex.org/W2015688877","https://openalex.org/W2030694415","https://openalex.org/W2089537772","https://openalex.org/W2090755665","https://openalex.org/W2150857077","https://openalex.org/W2155427043","https://openalex.org/W2167338739","https://openalex.org/W2402972567"],"related_works":["https://openalex.org/W1565198967","https://openalex.org/W2592226044","https://openalex.org/W7043793605","https://openalex.org/W2547601809","https://openalex.org/W2737429942","https://openalex.org/W2124957963","https://openalex.org/W2700992887","https://openalex.org/W7065410814","https://openalex.org/W2142986430","https://openalex.org/W2404324365"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,19,68,91,133,147,163],"simple":[3],"but":[4],"effective":[5],"weighted":[6,159],"finite":[7],"state":[8],"transducer":[9],"(WFST)":[10],"based":[11],"framework":[12],"for":[13,37,80,99,116,126],"handling":[14],"out-of-vocabulary":[15],"(OOV)":[16],"keywords":[17,64,103],"in":[18,41,104,119,132,156],"speech":[20,27,40,110],"search":[21,32],"task.":[22],"State-of-the-art":[23],"large":[24],"vocabulary":[25],"continuous":[26],"recognition":[28],"(LVCSR)":[29],"and":[30,44,136],"keyword":[31,83],"(KWS)":[33],"systems":[34],"are":[35,47,65,78],"developed":[36],"conversational":[38],"telephone":[39],"Tagalog.":[42],"Word-based":[43],"phone-based":[45],"indexes":[46],"created":[48],"from":[49],"word":[50,117,121,164,167],"lattices,":[51],"the":[52,56,100,105,120],"latter":[53],"by":[54],"using":[55,84],"LVCSR":[57],"system's":[58],"pronunciation":[59],"lexicon.":[60],"Pronunciations":[61],"of":[62,90,129],"OOV":[63,82,130],"hypothesized":[66],"via":[67],"standard":[69],"grapheme-to-phoneme":[70],"method.":[71],"In-vocabulary":[72],"proxies":[73,118],"(word":[74],"or":[75],"phone":[76,92,134,139,148],"sequences)":[77],"generated":[79],"each":[81],"WFST":[85],"techniques":[86],"that":[87,113],"permit":[88],"incorporation":[89],"confusion":[93,140],"matrix.":[94],"Empirical":[95],"results":[96],"when":[97,145,161],"searching":[98,115,125,146,162],"Babel/NIST":[101],"evaluation":[102],"Babel":[106],"10":[107],"hour":[108],"development-test":[109],"collection":[111],"show":[112],"(i)":[114],"index":[122,165],"significantly":[123],"outperforms":[124],"phonetic":[127],"representations":[128],"words":[131],"index,":[135,149],"(ii)":[137],"while":[138],"information":[141],"yields":[142,151],"minor":[143],"improvement":[144,155],"it":[150],"up":[152],"to":[153],"40%":[154],"actual":[157],"term":[158],"value":[160],"with":[166],"proxies.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":21},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":15},{"year":2014,"cited_by_count":11}],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2016-06-24T00:00:00"}