{"id":"https://openalex.org/W2252136600","doi":"https://doi.org/10.18653/v1/w15-3211","title":"Best Practices for Crowdsourcing Dialectal Arabic Speech Transcription","display_name":"Best Practices for Crowdsourcing Dialectal Arabic Speech Transcription","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2252136600","doi":"https://doi.org/10.18653/v1/w15-3211","mag":"2252136600"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w15-3211","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-3211","pdf_url":"https://www.aclweb.org/anthology/W15-3211.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second Workshop on Arabic Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W15-3211.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021437180","display_name":"Samantha Wray","orcid":"https://orcid.org/0000-0003-1750-3790"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":true,"raw_author_name":"Samantha Wray","raw_affiliation_strings":["Qatar Computing Research Institute Hamad Bin Khalifa University Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute Hamad Bin Khalifa University Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102924560","display_name":"Hamdy Mubarak","orcid":"https://orcid.org/0000-0002-9051-6240"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Hamdy Mubarak","raw_affiliation_strings":["Qatar Computing Research Institute Hamad Bin Khalifa University Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute Hamad Bin Khalifa University Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100693435","display_name":"Ahmed Ali","orcid":"https://orcid.org/0000-0002-9186-7544"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Ahmed Ali","raw_affiliation_strings":["Qatar Computing Research Institute Hamad Bin Khalifa University Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute Hamad Bin Khalifa University Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5021437180"],"corresponding_institution_ids":["https://openalex.org/I4210144839"],"apc_list":null,"apc_paid":null,"fwci":2.565,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.9161512,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"99","last_page":"107"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.9993000030517578,"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":0.9909999966621399,"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/crowdsourcing","display_name":"Crowdsourcing","score":0.9048396348953247},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.7986512184143066},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7489527463912964},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6687291860580444},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6681467294692993},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6491215229034424},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46637895703315735},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.46325334906578064},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17991787195205688},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09847700595855713}],"concepts":[{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.9048396348953247},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7986512184143066},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7489527463912964},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6687291860580444},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6681467294692993},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6491215229034424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46637895703315735},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.46325334906578064},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17991787195205688},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09847700595855713},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/w15-3211","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-3211","pdf_url":"https://www.aclweb.org/anthology/W15-3211.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second Workshop on Arabic Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.708.380","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.708.380","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/4898/","raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/w15-3211","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-3211","pdf_url":"https://www.aclweb.org/anthology/W15-3211.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second Workshop on Arabic Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2252136600.pdf","grobid_xml":"https://content.openalex.org/works/W2252136600.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W408046128","https://openalex.org/W1588275722","https://openalex.org/W1724528691","https://openalex.org/W1972993000","https://openalex.org/W1973200191","https://openalex.org/W1990501283","https://openalex.org/W2077325010","https://openalex.org/W2115915304","https://openalex.org/W2123777430","https://openalex.org/W2132903577","https://openalex.org/W2154624463","https://openalex.org/W2163361328","https://openalex.org/W2250414785","https://openalex.org/W2250930911","https://openalex.org/W2251658995","https://openalex.org/W2295508056","https://openalex.org/W2295744349","https://openalex.org/W2399262366","https://openalex.org/W2620757702","https://openalex.org/W3204154385"],"related_works":["https://openalex.org/W3032998312","https://openalex.org/W135177976","https://openalex.org/W4384486036","https://openalex.org/W1503094549","https://openalex.org/W2337920774","https://openalex.org/W4286908577","https://openalex.org/W2886410948","https://openalex.org/W2025875869","https://openalex.org/W2028097510","https://openalex.org/W2505877856"],"abstract_inverted_index":{"In":[0],"this":[1,71],"paper,":[2],"we":[3,73],"investigate":[4],"different":[5],"approaches":[6],"in":[7,77],"crowdsourcing":[8],"transcriptions":[9],"of":[10,55,65,80],"Dialectal":[11,26],"Arabic":[12,27],"speech":[13,47,68],"with":[14,83,86,98],"automatic":[15],"quality":[16,39,49,64,88],"control":[17,50,89],"to":[18,37,95],"ensure":[19],"good":[20],"transcription":[21,48,78],"at":[22],"the":[23,63,66,101],"source.":[24],"Since":[25],"has":[28],"no":[29,87],"standard":[30],"orthographic":[31],"representation,":[32],"it":[33],"is":[34],"very":[35],"challenging":[36],"perform":[38],"control.":[40],"We":[41,61],"propose":[42],"a":[43,75],"complete":[44],"recipe":[45],"for":[46,90,100],"that":[51],"includes":[52],"using":[53],"output":[54],"an":[56],"Automatic":[57],"Speech":[58],"Recognition":[59],"system.":[60],"evaluated":[62],"transcribed":[67],"and":[69,93],"through":[70],"recipe,":[72],"achieved":[74],"reduction":[76],"error":[79],"1.0%":[81],"compared":[82,97],"13.2%":[84],"baseline":[85],"Egyptian":[91],"data,":[92],"down":[94],"4%":[96],"7.8%":[99],"North":[102],"African":[103],"dialect.":[104]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
