{"id":"https://openalex.org/W2097743493","doi":"https://doi.org/10.1109/icassp.2004.1326098","title":"Cross-dialectal acoustic data sharing for Arabic speech recognition","display_name":"Cross-dialectal acoustic data sharing for Arabic speech recognition","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2097743493","doi":"https://doi.org/10.1109/icassp.2004.1326098","mag":"2097743493"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326098","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/A5050325468","display_name":"Katrin Kirchhoff","orcid":"https://orcid.org/0000-0002-6645-6030"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"K. Kirchhoff","raw_affiliation_strings":["Department of Electrical Engineering, University of Washington, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060715364","display_name":"Dimitra Vergyri","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D. Vergyri","raw_affiliation_strings":["SRI International, Inc., Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5050325468"],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":2.3106,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.89667958,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"765"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T11309","display_name":"Music and Audio Processing","score":0.9966999888420105,"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/T10860","display_name":"Speech and Audio Processing","score":0.9962999820709229,"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/arabic","display_name":"Arabic","score":0.7843777537345886},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7792661190032959},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6785262823104858},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.6602737903594971},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.554628312587738},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5474288463592529},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4870310425758362},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4604931175708771},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2768392562866211},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1843852996826172},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.057227373123168945}],"concepts":[{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7843777537345886},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7792661190032959},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6785262823104858},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.6602737903594971},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.554628312587738},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5474288463592529},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4870310425758362},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4604931175708771},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2768392562866211},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1843852996826172},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.057227373123168945},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2004.1326098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326098","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:10.1.1.172.1944","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.172.1944","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ssli.ee.washington.edu/people/katrin/Papers/kirchhoff-icassp04.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6499999761581421,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1846073453","https://openalex.org/W2033436836","https://openalex.org/W2121981798","https://openalex.org/W2126597185","https://openalex.org/W3151884159","https://openalex.org/W3152004739","https://openalex.org/W6638728282"],"related_works":["https://openalex.org/W2620283452","https://openalex.org/W4322750817","https://openalex.org/W4245232085","https://openalex.org/W2801712537","https://openalex.org/W587642979","https://openalex.org/W2894059694","https://openalex.org/W2044408773","https://openalex.org/W3173761424","https://openalex.org/W4299493485","https://openalex.org/W617130659"],"abstract_inverted_index":{"The":[0,56],"automatic":[1],"recognition":[2,50,106],"of":[3,39,51,59],"Arabic":[4,12,45,54],"dialectal":[5],"speech":[6,105],"is":[7,61,68,84],"a":[8],"challenging":[9],"task":[10],"since":[11],"dialects":[13],"are":[14,28],"essentially":[15],"spoken":[16],"varieties,":[17],"for":[18],"which":[19],"only":[20],"sparse":[21],"resources":[22],"(transcriptions":[23],"and":[24,73,76,108],"standardized":[25],"acoustic":[26,40],"data)":[27],"available":[29],"to":[30,47],"date.":[31],"In":[32],"this":[33],"paper":[34],"we":[35],"describe":[36],"the":[37,49,64,99],"use":[38,58],"data":[41,60,90],"from":[42],"modern":[43],"standard":[44],"(MSA)":[46],"improve":[48],"Egyptian":[52],"conversational":[53],"(ECA).":[55],"cross-dialectal":[57],"complicated":[62],"by":[63,86],"fact":[65],"that":[66,110],"MSA":[67,89],"written":[69],"without":[70],"short":[71],"vowels":[72],"other":[74],"diacritics":[75],"thus":[77],"has":[78],"incomplete":[79],"phonetic":[80],"information.":[81],"This":[82],"problem":[83],"addressed":[85],"automatically":[87],"vowelizing":[88],"before":[91],"combining":[92],"it":[93],"with":[94],"ECA":[95],"data.":[96],"We":[97],"described":[98],"vowelization":[100],"procedure":[101],"as":[102,104],"well":[103],"experiments":[107],"show":[109],"our":[111,116],"technique":[112],"yields":[113],"improvements":[114],"over":[115],"baseline":[117],"system.":[118]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":5},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}