{"id":"https://openalex.org/W1990501283","doi":"https://doi.org/10.1109/slt.2014.7078629","title":"A complete KALDI recipe for building Arabic speech recognition systems","display_name":"A complete KALDI recipe for building Arabic speech recognition systems","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W1990501283","doi":"https://doi.org/10.1109/slt.2014.7078629","mag":"1990501283"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2014.7078629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","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/A5100693435","display_name":"Ahmed Ali","orcid":"https://orcid.org/0000-0002-9186-7544"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ahmed Ali","raw_affiliation_strings":["Qatar Computing Research Institute","Qatar computing research institute, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute","institution_ids":[]},{"raw_affiliation_string":"Qatar computing research institute, Qatar","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376931","display_name":"Yifan Zhang","orcid":"https://orcid.org/0000-0002-2125-1074"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifan Zhang","raw_affiliation_strings":["Qatar Computing Research Institute","Qatar computing research institute, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute","institution_ids":[]},{"raw_affiliation_string":"Qatar computing research institute, Qatar","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051056084","display_name":"Patrick Cardinal","orcid":"https://orcid.org/0009-0000-9439-9910"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick Cardinal","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, Massachusetts, USA","MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, Massachusetts 02139, USA"],"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, Massachusetts, USA","institution_ids":[]},{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, Massachusetts 02139, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113547334","display_name":"Najim Dahak","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Najim Dahak","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, Massachusetts, USA","MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, Massachusetts 02139, USA"],"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, Massachusetts, USA","institution_ids":[]},{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, Massachusetts 02139, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064572063","display_name":"Stephan Vogel","orcid":"https://orcid.org/0000-0003-2630-4881"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stephan Vogel","raw_affiliation_strings":["Qatar Computing Research Institute","Qatar computing research institute, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute","institution_ids":[]},{"raw_affiliation_string":"Qatar computing research institute, Qatar","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, Massachusetts, USA","MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, Massachusetts 02139, USA"],"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, Massachusetts, USA","institution_ids":[]},{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, Massachusetts 02139, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100693435"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.9542,"has_fulltext":false,"cited_by_count":103,"citation_normalized_percentile":{"value":0.98859622,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"525","last_page":"529"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9991000294685364,"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":0.9933000206947327,"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/recipe","display_name":"Recipe","score":0.8639335632324219},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.8598686456680298},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8286871314048767},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.7027336955070496},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5787290334701538},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5370798110961914},{"id":"https://openalex.org/keywords/writing-system","display_name":"Writing system","score":0.5220372676849365},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5109862089157104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.436308890581131},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.336946964263916},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.28807657957077026},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10344243049621582}],"concepts":[{"id":"https://openalex.org/C2778671685","wikidata":"https://www.wikidata.org/wiki/Q219239","display_name":"Recipe","level":2,"score":0.8639335632324219},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.8598686456680298},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8286871314048767},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7027336955070496},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5787290334701538},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5370798110961914},{"id":"https://openalex.org/C78148190","wikidata":"https://www.wikidata.org/wiki/Q8192","display_name":"Writing system","level":2,"score":0.5220372676849365},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5109862089157104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.436308890581131},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.336946964263916},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.28807657957077026},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10344243049621582},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C31903555","wikidata":"https://www.wikidata.org/wiki/Q1637030","display_name":"Food science","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt.2014.7078629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.706.9827","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.706.9827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.qcri.qa/app/media/4901/","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W72757270","https://openalex.org/W125610139","https://openalex.org/W1524333225","https://openalex.org/W1978716251","https://openalex.org/W1993561131","https://openalex.org/W2020079054","https://openalex.org/W2042777049","https://openalex.org/W2087274442","https://openalex.org/W2109613320","https://openalex.org/W2124973918","https://openalex.org/W2153186553","https://openalex.org/W2163238203","https://openalex.org/W2189369791","https://openalex.org/W2917348560","https://openalex.org/W4245136196","https://openalex.org/W6602923018","https://openalex.org/W6631362777","https://openalex.org/W6686677357"],"related_works":["https://openalex.org/W2048641630","https://openalex.org/W2086733238","https://openalex.org/W3197562407","https://openalex.org/W4386106688","https://openalex.org/W2064646575","https://openalex.org/W2359001871","https://openalex.org/W4316012193","https://openalex.org/W1990501283","https://openalex.org/W2787579211","https://openalex.org/W942698554"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,61,66,70],"present":[4],"a":[5,24],"recipe":[6],"and":[7,12,58,81,90,111],"language":[8,73,97],"resources":[9,91,98],"for":[10,55],"training":[11,110],"testing":[13,112],"Arabic":[14],"speech":[15],"recognition":[16],"systems":[17],"using":[18,29,51,78],"the":[19,44,49,52,72,103],"KALDI":[20,89],"toolkit.":[21],"We":[22,40,75],"built":[23],"prototype":[25],"broadcast":[26],"news":[27],"system":[28],"200":[30],"hours":[31],"GALE":[32],"data":[33],"that":[34],"is":[35,102],"publicly":[36],"available":[37,94],"through":[38,88],"LDC.":[39],"describe":[41],"in":[42,47],"detail":[43],"decisions":[45],"made":[46,93],"building":[48],"system:":[50],"MADA":[53],"toolkit":[54],"text":[56],"normalization":[57],"vowelization;":[59],"why":[60],"use":[62],"36":[63],"phonemes;":[64],"how":[65,69],"generate":[67],"pronunciations;":[68],"build":[71],"model.":[74],"report":[76],"results":[77,113],"state-of-the-art":[79],"modeling":[80],"decoding":[82],"techniques.":[83],"The":[84],"scripts":[85],"are":[86,92],"released":[87],"on":[95,114],"QCRI's":[96],"web":[99],"portal.":[100],"This":[101],"first":[104],"effort":[105],"to":[106],"share":[107],"reproducible":[108],"sizable":[109],"MSA":[115],"system.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
