{"id":"https://openalex.org/W81527949","doi":"https://doi.org/10.21437/interspeech.2009-558","title":"Towards using hybrid word and fragment units for vocabulary independent LVCSR systems","display_name":"Towards using hybrid word and fragment units for vocabulary independent LVCSR systems","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W81527949","doi":"https://doi.org/10.21437/interspeech.2009-558","mag":"81527949"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-558","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","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/A5110230355","display_name":"Ariya Rastrow","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":"Ariya Rastrow","raw_affiliation_strings":["Johns Hopkins University, Baltimore, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, United States","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088302697","display_name":"Abhinav Sethy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abhinav Sethy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["IBM (United States), Armonk, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM (United States), Armonk, United States","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110017489","display_name":"Frederick Jelinek","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":"Frederick Jelinek","raw_affiliation_strings":["Johns Hopkins University, Baltimore, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, United States","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1931","last_page":"1934"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9954000115394592,"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":0.8387725353240967},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7413581609725952},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7224493622779846},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6223026514053345},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.609831690788269},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.5877933502197266},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5653027296066284},{"id":"https://openalex.org/keywords/hybrid-system","display_name":"Hybrid system","score":0.4802175462245941},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46639224886894226},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41438475251197815},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10632908344268799},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.07641857862472534}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8387725353240967},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7413581609725952},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7224493622779846},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6223026514053345},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.609831690788269},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.5877933502197266},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5653027296066284},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.4802175462245941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46639224886894226},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41438475251197815},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10632908344268799},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.07641857862472534},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2009-558","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.433.5003","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.433.5003","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/~arastrow/Publications/hybrid_interspeech09.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W23025778","https://openalex.org/W49437105","https://openalex.org/W67332896","https://openalex.org/W183136171","https://openalex.org/W1501139663","https://openalex.org/W1571931074","https://openalex.org/W1797288984","https://openalex.org/W2015688877","https://openalex.org/W2098318492","https://openalex.org/W2125534887","https://openalex.org/W2126315862","https://openalex.org/W2140281218","https://openalex.org/W2142986430","https://openalex.org/W2145094523","https://openalex.org/W2169384404"],"related_works":["https://openalex.org/W2073713056","https://openalex.org/W3110702597","https://openalex.org/W2078761926","https://openalex.org/W2110441383","https://openalex.org/W2125620709","https://openalex.org/W1498872724","https://openalex.org/W4233149903","https://openalex.org/W4293864700","https://openalex.org/W2061937230","https://openalex.org/W2189081180"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,50,68,85,128,143],"advantages":[4],"of":[5,95,134],"augmenting":[6],"a":[7,14,26,40,102],"word-based":[8],"system":[9,28,52],"with":[10],"sub-word":[11],"units":[12,38],"as":[13],"step":[15],"towards":[16],"building":[17],"open":[18],"vocabulary":[19],"speech":[20],"recognition":[21],"systems.":[22,47],"We":[23],"show":[24],"that":[25],"hybrid":[27,51,86,148],"which":[29],"combines":[30],"words":[31,83],"and":[32,60,72,119],"data-driven,":[33],"variable":[34],"length":[35],"sub":[36],"word":[37,45],"has":[39],"better":[41,54],"phone":[42,108,155],"accuracy":[43],"than":[44],"only":[46],"In":[48],"addition":[49],"is":[53,88,140],"in":[55,107,116,124,138,142],"detecting":[56],"Out-Of-Vocabulary":[57],"(OOV)":[58],"terms":[59],"representing":[61],"them":[62],"phonetically.":[63],"Results":[64],"are":[65],"presented":[66],"on":[67,98],"RT-04":[69,99],"broadcast":[70],"news":[71],"MIT":[73],"Lecture":[74],"data":[75],"sets.":[76],"An":[77],"FSM-based":[78],"approach":[79],"to":[80],"recover":[81],"OOV":[82,93,129,144,157],"from":[84],"lattices":[87],"also":[89],"presented.":[90],"At":[91],"an":[92],"rate":[94,110],"2.5":[96],"%":[97,104,113,121,136],"we":[100],"observed":[101],"8":[103],"relative":[105,114,122,137],"improvement":[106,115,123],"error":[109],"(PER),":[111],"7.3":[112],"oracle":[117],"PER":[118,139],"7":[120],"WER":[125],"after":[126],"recovering":[127],"terms.":[130],"A":[131],"significant":[132],"reduction":[133],"33":[135],"seen":[141],"regions.":[145],"Index":[146],"Terms:":[147],"LVCSR":[149],"system,":[150],"out-of-vocabulary,":[151],"subword":[152],"unit":[153],"selection,":[154],"recognition,":[156],"detection":[158]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}