{"id":"https://openalex.org/W1995248852","doi":"https://doi.org/10.1109/asru.2011.6163939","title":"An investigation of heuristic, manual and statistical pronunciation derivation for Pashto","display_name":"An investigation of heuristic, manual and statistical pronunciation derivation for Pashto","publication_year":2011,"publication_date":"2011-12-01","ids":{"openalex":"https://openalex.org/W1995248852","doi":"https://doi.org/10.1109/asru.2011.6163939","mag":"1995248852"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2011.6163939","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2011.6163939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding","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/A5110218731","display_name":"Upendra V. Chaudhari","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"]},{"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":"Upendra V. Chaudhari","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM T.J.Watson Research Center, 1101 Kitchawan Road, Rt. 134, Yorktown Heights, NY 10598, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T.J.Watson Research Center, 1101 Kitchawan Road, Rt. 134, Yorktown Heights, NY 10598, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102014291","display_name":"Xiaodong Cui","orcid":"https://orcid.org/0000-0003-4865-1307"},"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"]},{"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":"Xiaodong Cui","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM T.J.Watson Research Center, 1101 Kitchawan Road, Rt. 134, Yorktown Heights, NY 10598, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T.J.Watson Research Center, 1101 Kitchawan Road, Rt. 134, Yorktown Heights, NY 10598, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107808331","display_name":"Bowen Zhou","orcid":"https://orcid.org/0000-0003-1062-9526"},"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"]},{"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":"Bowen Zhou","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM T.J.Watson Research Center, 1101 Kitchawan Road, Rt. 134, Yorktown Heights, NY 10598, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T.J.Watson Research Center, 1101 Kitchawan Road, Rt. 134, Yorktown Heights, NY 10598, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":null,"display_name":"Rong Zhang","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"]},{"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":"Rong Zhang","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM T.J.Watson Research Center, 1101 Kitchawan Road, Rt. 134, Yorktown Heights, NY 10598, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T.J.Watson Research Center, 1101 Kitchawan Road, Rt. 134, Yorktown Heights, NY 10598, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"249","last_page":"253"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983999729156494,"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/T10028","display_name":"Topic Modeling","score":0.9923999905586243,"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":0.8647222518920898},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6811522841453552},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.643775999546051},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5855844616889954},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.572702944278717},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5274912118911743},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.48752638697624207},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.47301653027534485},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4466712474822998},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42799291014671326},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.42796722054481506},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41148310899734497}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8647222518920898},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6811522841453552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.643775999546051},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5855844616889954},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.572702944278717},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5274912118911743},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.48752638697624207},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.47301653027534485},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4466712474822998},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42799291014671326},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.42796722054481506},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41148310899734497},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2011.6163939","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2011.6163939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W67332896","https://openalex.org/W1240618447","https://openalex.org/W1506201763","https://openalex.org/W1779680350","https://openalex.org/W2026019257","https://openalex.org/W2073845625","https://openalex.org/W2097927681","https://openalex.org/W2098287788","https://openalex.org/W2103592412","https://openalex.org/W2123242372","https://openalex.org/W2125234026","https://openalex.org/W2127646729","https://openalex.org/W2132959327","https://openalex.org/W2157075408","https://openalex.org/W2917348560","https://openalex.org/W2950186769","https://openalex.org/W3152004739","https://openalex.org/W6602743565","https://openalex.org/W6630412972","https://openalex.org/W6638280674","https://openalex.org/W6674948912"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2794347674","https://openalex.org/W2972060578","https://openalex.org/W4285877427","https://openalex.org/W783305165","https://openalex.org/W4287644835","https://openalex.org/W3092281475","https://openalex.org/W3098003361","https://openalex.org/W2274846632","https://openalex.org/W4254087122"],"abstract_inverted_index":{"In":[0],"this":[1,59],"paper,":[2],"we":[3,156,180],"study":[4],"the":[5,21,71,114,132,141,150,159,177,195],"issue":[6],"of":[7,23,42,52,104,131,185],"generating":[8,82],"pronunciations":[9,66,190],"for":[10,18,31,67,81],"training":[11,44],"and":[12,74,95,138,143],"decoding":[13],"with":[14,34,48,61],"an":[15,87,147],"ASR":[16,136],"system":[17,29,137],"Pashto":[19],"in":[20,70,176],"context":[22],"a":[24,39,49,107,119,129,182],"Speech":[25,27],"to":[26,90,152],"Translation":[28,123],"developed":[30],"TRANSTAC.":[32],"As":[33],"other":[35,62,115],"low":[36],"resourced":[37],"languages,":[38],"limited":[40],"amount":[41],"acoustic":[43],"data":[45,60],"was":[46],"available":[47],"corresponding":[50],"set":[51],"manually":[53,188],"produced":[54],"vowelized":[55],"pronunciations.":[56],"We":[57,125],"augment":[58],"sources,":[63],"but":[64],"lack":[65],"unseen":[68],"words":[69],"new":[72],"audio":[73],"associated":[75],"text.":[76],"Four":[77],"methods":[78,97,145,162],"are":[79],"investigated":[80],"these":[83,105],"pronunciations,":[84],"or":[85,167],"baseforms:":[86],"heuristic":[88],"grapheme":[89,151],"phoneme":[91,153],"map,":[92],"manual":[93,142,170],"annotation,":[94],"two":[96],"based":[98,117],"on":[99,118,128],"statistical":[100,144,161],"models.":[101],"The":[102],"first":[103],"uses":[106],"joint":[108],"Maximum":[109],"Entropy":[110],"N-gram":[111],"model":[112],"while":[113],"is":[116],"log-linear":[120],"Statistical":[121],"Machine":[122],"model.":[124],"report":[126],"results":[127],"state":[130],"art,":[133],"discriminatively":[134],"trained,":[135],"show":[139],"that":[140,158],"provide":[146],"improvement":[148],"over":[149],"map.":[154],"Moreover,":[155],"demonstrate":[157],"automatic":[160],"can":[163],"perform":[164],"as":[165],"well":[166],"better":[168],"than":[169],"generation":[171],"by":[172,194],"native":[173],"speakers,":[174],"even":[175],"case":[178],"where":[179],"have":[181],"significant":[183],"number":[184],"high":[186],"quality,":[187],"generated":[189],"beyond":[191],"those":[192],"provided":[193],"TRANSTAC":[196],"program.":[197]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}