{"id":"https://openalex.org/W2128014038","doi":"https://doi.org/10.1109/icassp.2006.1660214","title":"Morphological Decomposition for Arabic Broadcast News Transcription","display_name":"Morphological Decomposition for Arabic Broadcast News Transcription","publication_year":2006,"publication_date":"2006-08-03","ids":{"openalex":"https://openalex.org/W2128014038","doi":"https://doi.org/10.1109/icassp.2006.1660214","mag":"2128014038"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2006.1660214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","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/A5107249743","display_name":"Bing Xiang","orcid":"https://orcid.org/0009-0006-4028-4935"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Bing Xiang","raw_affiliation_strings":["BBN Technologies, GTE, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"BBN Technologies, GTE, Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103554889","display_name":"Kham Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kham Nguyen","raw_affiliation_strings":["BBN Technologies, GTE, Cambridge, MA, USA","Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"BBN Technologies, GTE, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048517713","display_name":"Long Nguyen","orcid":"https://orcid.org/0000-0002-0884-1635"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Long Nguyen","raw_affiliation_strings":["BBN Technologies, GTE, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"BBN Technologies, GTE, Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089653752","display_name":"Richard Schwartz","orcid":"https://orcid.org/0000-0002-4654-624X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R. Schwartz","raw_affiliation_strings":["BBN Technologies, GTE, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"BBN Technologies, GTE, Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111497957","display_name":"J. Makhoul","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J. Makhoul","raw_affiliation_strings":["BBN Technologies, GTE, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"BBN Technologies, GTE, Cambridge, MA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5107249743"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.3901,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.98206186,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"1089"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9829999804496765,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9599999785423279,"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":0.8112136125564575},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7956457138061523},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.7422435283660889},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.723068356513977},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6988441348075867},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5922613143920898},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5506035685539246},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5401811003684998},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5180778503417969},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4795553386211395},{"id":"https://openalex.org/keywords/word-recognition","display_name":"Word recognition","score":0.43104803562164307},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11556777358055115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8112136125564575},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7956457138061523},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7422435283660889},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.723068356513977},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6988441348075867},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5922613143920898},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5506035685539246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5401811003684998},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5180778503417969},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4795553386211395},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.43104803562164307},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11556777358055115},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"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/icassp.2006.1660214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W12369754","https://openalex.org/W171797550","https://openalex.org/W294504433","https://openalex.org/W1707124376","https://openalex.org/W1719940802","https://openalex.org/W1895315011","https://openalex.org/W1956785191","https://openalex.org/W2098439409","https://openalex.org/W2140914930","https://openalex.org/W2144810223","https://openalex.org/W6600511774","https://openalex.org/W6607090388","https://openalex.org/W6610520150","https://openalex.org/W6637472752","https://openalex.org/W6641027123","https://openalex.org/W6680972403"],"related_works":["https://openalex.org/W1566315437","https://openalex.org/W2594897229","https://openalex.org/W4221142855","https://openalex.org/W2151348424","https://openalex.org/W2050138804","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W2523799048","https://openalex.org/W2155620340","https://openalex.org/W1494910745"],"abstract_inverted_index":{"In":[0,37,116],"this":[1,38,75,101],"paper,":[2],"we":[3],"present":[4],"a":[5,30,107],"novel":[6],"approach":[7],"for":[8],"morphological":[9],"de-composition":[10],"in":[11,29,49,60,74,86,125],"large":[12],"vocabulary":[13],"Arabic":[14,32],"speech":[15],"recognition.":[16],"It":[17],"achieved":[18,80],"low":[19],"out-of-vocabulary":[20],"(OOV)":[21],"rate":[22,89],"as":[23,25],"well":[24],"high":[26],"recognition":[27,62,98,109],"accuracy":[28],"state-of-the-art":[31],"broadcast":[33],"news":[34],"transcription":[35],"system.":[36],"approach,":[39],"the":[40,61,94,113,117,119,135],"compound":[41],"words":[42,59],"are":[43,64,70],"decomposed":[44,58,120],"into":[45],"stems":[46],"and":[47,53,72,129],"affixes":[48],"both":[50],"language":[51],"training":[52,55],"acoustic":[54],"data.":[56],"The":[57,77,97],"output":[63],"re-joined":[65],"before":[66],"scoring.":[67],"Four":[68],"algorithms":[69],"experimented":[71],"compared":[73,92],"work.":[76],"best":[78],"system":[79,102,110,121],"1.9%":[81],"absolute":[82],"reduction":[83],"(9.8%":[84],"relative)":[85],"word":[87],"error":[88],"(WER)":[90],"when":[91],"to":[93,106],"64K-word":[95],"baseline.":[96],"performance":[99],"of":[100,127],"is":[103,122],"also":[104,130],"comparable":[105],"300K-word":[108],"trained":[111],"on":[112],"normal":[114],"words.":[115],"meantime,":[118],"much":[123],"faster":[124],"terms":[126],"speed":[128],"needs":[131],"less":[132],"memory":[133],"than":[134,139],"systems":[136],"with":[137],"larger":[138],"64K":[140],"vocabularies.":[141]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}