{"id":"https://openalex.org/W2158420521","doi":"https://doi.org/10.1109/tasl.2009.2022966","title":"Advances in Arabic Speech Transcription at IBM Under the DARPA GALE Program","display_name":"Advances in Arabic Speech Transcription at IBM Under the DARPA GALE Program","publication_year":2009,"publication_date":"2009-06-16","ids":{"openalex":"https://openalex.org/W2158420521","doi":"https://doi.org/10.1109/tasl.2009.2022966","mag":"2158420521"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2009.2022966","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2009.2022966","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5010878109","display_name":"Hagen Soltau","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hagen Soltau","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Saon","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110252428","display_name":"Hong-Kwang Jeff Kuo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong-Kwang Jeff Kuo","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019973376","display_name":"Lidia Mangu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lidia Mangu","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"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/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080675607","display_name":"Ahmad Emami","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmad Emami","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5010878109"],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":6.9789,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.97026787,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"17","issue":"5","first_page":"884","last_page":"894"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10201","display_name":"Speech Recognition and Synthesis","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/T11309","display_name":"Music and Audio Processing","score":0.9972000122070312,"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/computer-science","display_name":"Computer science","score":0.8208991885185242},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6740140318870544},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5662052035331726},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5640271902084351},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.5562397241592407},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5527158379554749},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.552286684513092},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5076581239700317},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.45597705245018005},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4490521550178528},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.43910884857177734},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43601125478744507},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.41847431659698486},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07855334877967834}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8208991885185242},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6740140318870544},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5662052035331726},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5640271902084351},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.5562397241592407},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5527158379554749},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.552286684513092},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5076581239700317},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.45597705245018005},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4490521550178528},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.43910884857177734},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43601125478744507},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.41847431659698486},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07855334877967834},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2009.2022966","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2009.2022966","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.550000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W13802415","https://openalex.org/W97921715","https://openalex.org/W141449985","https://openalex.org/W171797550","https://openalex.org/W1571931074","https://openalex.org/W1596641231","https://openalex.org/W1895315011","https://openalex.org/W1948894153","https://openalex.org/W1970689298","https://openalex.org/W2002342963","https://openalex.org/W2087596289","https://openalex.org/W2104448323","https://openalex.org/W2106554350","https://openalex.org/W2110765229","https://openalex.org/W2125234026","https://openalex.org/W2125610823","https://openalex.org/W2134756243","https://openalex.org/W2140679639","https://openalex.org/W2142983806","https://openalex.org/W2144790469","https://openalex.org/W2147467930","https://openalex.org/W4239209816","https://openalex.org/W6603990542","https://openalex.org/W6635914189","https://openalex.org/W6675701829","https://openalex.org/W6679945967","https://openalex.org/W6680532216"],"related_works":["https://openalex.org/W3126131865","https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2000075989","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W1607396156","https://openalex.org/W2776838583","https://openalex.org/W2359469050"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,12,22,29,89,96,155,166,173,192,204],"Arabic":[4,78,151],"broadcast":[5],"transcription":[6],"system":[7,70,106],"fielded":[8],"by":[9,161,190,209],"IBM":[10],"in":[11,172],"GALE":[13],"Phase":[14],"2.5":[15,45],"machine":[16],"translation":[17],"evaluation.":[18],"Key":[19],"advances":[20],"include":[21],"use":[23,34,167],"of":[24,35,91,98,114,128,141,157,168],"additional":[25],"training":[26,86,104],"data":[27,93,100,116,130,158],"from":[28],"Linguistic":[30],"Data":[31],"Consortium":[32],"(LDC),":[33],"a":[36,64,109,123,135,147,185,196,200,210],"very":[37,136],"large":[38,81,137],"vocabulary":[39],"comprising":[40],"737":[41],"K":[42],"words":[43],"and":[44,57,61,199],"M":[46],"pronunciation":[47],"variants,":[48],"automatic":[49],"vowelization":[50],"using":[51],"flat-start":[52],"training,":[53],"cross-adaptation":[54],"between":[55],"unvowelized":[56],"vowelized":[58],"acoustic":[59,163],"models,":[60],"rescoring":[62],"with":[63,84,134,184,203],"neural-network":[65],"language":[66],"model.":[67],"The":[68],"resulting":[69],"achieves":[71],"word":[72],"error":[73],"rates":[74],"below":[75],"10%":[76],"on":[77,95],"broadcasts.":[79],"Very":[80],"scale":[82],"experiments":[83],"unsupervised":[85,92,103,142],"demonstrate":[87],"that":[88,153,212],"utility":[90],"depends":[94],"amount":[97,111,125],"supervised":[99,115,129],"available.":[101],"While":[102],"improves":[105],"performance":[107],"when":[108,122],"limited":[110],"(135":[112],"h)":[113,127,139],"is":[117,131,213],"available,":[118],"these":[119],"gains":[120],"disappear":[121],"greater":[124],"(848":[126],"used,":[132],"even":[133],"(7069":[138],"corpus":[140],"data.":[143],"We":[144,176],"also":[145],"describe":[146],"method":[148,180],"for":[149],"modeling":[150],"dialects":[152],"avoids":[154],"problem":[156],"sparseness":[159],"entailed":[160],"dialect-specific":[162],"models":[164],"via":[165],"non-phonetic,":[169],"dialect":[170],"questions":[171],"decision":[174,193],"trees.":[175],"show":[177],"how":[178],"this":[179],"can":[181],"be":[182],"used":[183],"statically":[186],"compiled":[187],"decoding":[188],"graph":[189],"partitioning":[191],"trees":[194],"into":[195],"static":[197],"component":[198,206],"dynamic":[201,205],"component,":[202],"being":[207],"replaced":[208],"mapping":[211],"evaluated":[214],"at":[215],"run-time.":[216]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}