{"id":"https://openalex.org/W2166850712","doi":"https://doi.org/10.1109/icassp.2004.1326093","title":"Hybrid language models for out of vocabulary word detection in large vocabulary conversational speech recognition","display_name":"Hybrid language models for out of vocabulary word detection in large vocabulary conversational speech recognition","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2166850712","doi":"https://doi.org/10.1109/icassp.2004.1326093","mag":"2166850712"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},"type":"article","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/A5043817305","display_name":"Akan Yazgan","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":true,"raw_author_name":"A. Yazgan","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055086464","display_name":"Murat Sara\u00e7lar","orcid":"https://orcid.org/0000-0002-7435-8510"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Saraclar","raw_affiliation_strings":["AT and T Research Laboratories, Florham Park, NJ, USA"],"affiliations":[{"raw_affiliation_string":"AT and T Research Laboratories, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5043817305"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":3.697,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.93455351,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"745"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994999766349792,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9965999722480774,"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":0.8608344793319702},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7889639139175415},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.741479754447937},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7238494753837585},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6517701148986816},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.566816508769989},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5458347201347351},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.525844156742096},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4955991506576538},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09263455867767334},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07591226696968079}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8608344793319702},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7889639139175415},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.741479754447937},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7238494753837585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6517701148986816},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.566816508769989},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5458347201347351},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.525844156742096},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4955991506576538},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09263455867767334},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07591226696968079},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2004.1326093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.163.8907","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.163.8907","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/~ali/pubs/OOV_paper.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.329.8106","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.329.8106","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://busim.ee.boun.edu.tr/~murat/publications/icassp04ali.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W17921661","https://openalex.org/W77114827","https://openalex.org/W1501139663","https://openalex.org/W1526727648","https://openalex.org/W1887100226","https://openalex.org/W2004329216","https://openalex.org/W2050958850","https://openalex.org/W3152381020","https://openalex.org/W4301749008","https://openalex.org/W6603046125","https://openalex.org/W6844943890"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2097963413","https://openalex.org/W2294335174","https://openalex.org/W2025614924","https://openalex.org/W3145575561","https://openalex.org/W2001275470","https://openalex.org/W2073996508","https://openalex.org/W1997182898","https://openalex.org/W2944691285"],"abstract_inverted_index":{"In":[0,102],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,14,26,42,72,93,104],"method":[6,24,91],"for":[7,85],"out-of-vocabulary":[8],"(OOV)":[9],"word":[10,69,74,100,110],"detection":[11,43],"and":[12,32,58],"take":[13],"step":[15],"toward":[16],"open":[17],"vocabulary":[18,87],"automatic":[19],"speech":[20],"recognition.":[21],"The":[22,89],"proposed":[23],"uses":[25],"hybrid":[27,56],"language":[28],"model":[29],"combining":[30],"words":[31,53],"subword":[33],"units":[34],"such":[35],"as":[36],"phones":[37],"or":[38],"syllables.":[39],"We":[40],"describe":[41],"algorithm":[44],"based":[45],"on":[46,79],"the":[47,51,55,63,67,80,108],"posterior":[48,64],"count":[49],"of":[50,66,95,107],"OOV":[52,99,109],"given":[54,71],"model,":[57],"compare":[59],"it":[60],"to":[61],"using":[62],"probability":[65],"best":[68],"string":[70],"conventional":[73],"only":[75],"model.":[76],"Experimental":[77],"results":[78],"Switchboard":[81],"corpus":[82],"are":[83,112],"presented":[84],"different":[86],"sizes.":[88],"new":[90],"yields":[92],"gain":[94],"over":[96],"10%":[97],"in":[98],"detection.":[101],"addition,":[103],"modest":[105],"number":[106],"pronunciations":[111],"found":[113],"correctly.":[114]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}