{"id":"https://openalex.org/W155946340","doi":"https://doi.org/10.21437/interspeech.2006-390","title":"Improving Arabic HMM based speech synthesis quality","display_name":"Improving Arabic HMM based speech synthesis quality","publication_year":2006,"publication_date":"2006-09-17","ids":{"openalex":"https://openalex.org/W155946340","doi":"https://doi.org/10.21437/interspeech.2006-390","mag":"155946340"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2006-390","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","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/A5077733105","display_name":"Ossama Abdel\u2010Hamid","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ossama Abdel-Hamid","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048958429","display_name":"Sherif Abdou","orcid":"https://orcid.org/0000-0002-8338-856X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sherif Mahdy Abdou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5030016694","display_name":"Mohsen Rashwan","orcid":"https://orcid.org/0000-0003-3712-5408"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohsen Rashwan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9976000189781189,"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/T11309","display_name":"Music and Audio Processing","score":0.9927999973297119,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8418605327606201},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.8339966535568237},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7993283867835999},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7815088033676147},{"id":"https://openalex.org/keywords/voice","display_name":"Voice","score":0.5669000744819641},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4713268578052521},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4273834228515625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3977305293083191}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8418605327606201},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.8339966535568237},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7993283867835999},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7815088033676147},{"id":"https://openalex.org/C552089266","wikidata":"https://www.wikidata.org/wiki/Q494510","display_name":"Voice","level":2,"score":0.5669000744819641},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4713268578052521},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4273834228515625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3977305293083191},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2006-390","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"},{"score":0.4699999988079071,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W133559434","https://openalex.org/W1496971974","https://openalex.org/W1600722501","https://openalex.org/W2129082420","https://openalex.org/W2154920538","https://openalex.org/W2160972557","https://openalex.org/W2164764235","https://openalex.org/W2166823384"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W3184123547","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861","https://openalex.org/W2488941600"],"abstract_inverted_index":{"Abstract":[0],"HMM":[1,12,107,128,147,340,419,463,522],"based":[2,78,108,441,464,500,523],"speech":[3,6,21,64,101,109,136,155,183,200,203,238,246,294,345,354,358,427,465,524],"synthesis,":[4,59,102,239,422],"where":[5,240,373,477],"parameters":[7,142,346,359],"are":[8,66,130,143,279,414,429,542],"generated":[9,77,144,440,453],"directly":[10,416],"from":[11,50,145,158,189,218],"models,":[13],"is":[14,76,112,156,164,235,269,289,313,377,387,439,452,499,509,527,536,549],"a":[15,41,80,113,216,257,270,331,380,406,443,455],"new":[16,114],"technique":[17,115,371],"relative":[18,116],"to":[19,31,35,69,117,132,139,150,166,195,207,243,320,341,350,365,400,432,468,483,486],"other":[20,118],"synthesis":[22,110,119,466,525],"techniques.":[23],"In":[24,57,125,202,334,421,516],"this":[25,126,514],"paper,":[26],"we":[27,46,338,404],"propose":[28],"some":[29,178,277,290],"modifications":[30,94],"the":[32,51,58,60,92,96,151,167,181,190,196,211,248,252,261,274,293,298,352,374,418,423,449,461,473,488,517,520,533],"basic":[33,162,521],"system":[34,163,168,467,526,535],"improve":[36],"its":[37],"quality.":[38,97,184,355],"We":[39,459],"apply":[40,366],"multi-band":[42],"excitation":[43,282,299,322],"model.":[44,83],"And":[45],"use":[47,339,405],"samples":[48,412],"extracted":[49],"spectral":[52,55,402,410],"envelop":[53,411],"as":[54,223,226,276,300,389,454],"parameters.":[56,72,137,160,435],"voiced":[61,74,266,391,424,437],"and":[62,121,220,284,384,425,497,508,547],"unvoiced":[63,426,450],"parts":[65,428],"mixed":[67,281,430],"according":[68,149,431],"bands":[70,433],"voicing":[71,327,361,434],"The":[73,161,233,356,436,493],"part":[75,438,451],"on":[79,87,263,285,292,442,501],"harmonic":[81,444],"sinusoidal":[82,445],"Experimental":[84],"tests":[85],"performed":[86],"Arabic":[88,469,471,494],"dataset":[89],"show":[90],"that":[91,175,214,228],"applied":[93,460],"improved":[95],"Index":[98],"Terms":[99],":":[100],"HMM,":[103],"MBE.":[104],"1.":[105,555],"Introduction":[106],"[1]":[111],"techniques,":[120],"it":[122,176],"seems":[123],"promising.":[124],"technique,":[127],"models":[129,148],"used":[131,198,357],"simultaneously":[133],"model":[134,342,446],"different":[135,231,236],"Then":[138],"synthesize":[140],"speech,":[141],"these":[146,159],"input":[152,478],"text,":[153],"then":[154,532],"synthesized":[157,182,245],"similar":[165,194],"described":[169,537],"in":[170,180,199,237,273,348,417,529,538,544,551],"[2].":[171],"It":[172],"was":[173],"found":[174],"had":[177],"problems":[179],"This":[185],"degraded":[186],"quality":[187],"comes":[188],"usage":[191],"of":[192,210,251,280,362,382,396,409,475,511,513],"features":[193],"ones":[197],"recognition.":[201],"recognition":[204],"it's":[205,241,317],"desired":[206,242],"get":[208],"rid":[209],"small":[212],"details":[213,250],"differentiate":[215],"user":[217],"another,":[219],"only":[221,324],"keep":[222],"little":[224],"information":[225],"possible":[227],"discriminate":[229],"between":[230],"phonemes.":[232],"case":[234],"generate":[244],"with":[247,304,310],"full":[249],"original":[253],"voice.":[254],"Also":[255,394],"using":[256,330,397],"hard":[258],"decision":[259],"for":[260,506],"frame":[262,375],"being":[264],"either":[265,301,390],"or":[267,307,392],"not":[268,314,323],"limiting":[271],"factor":[272],"system,":[275],"phonemes":[278,287,491],"type,":[283],"most":[286],"there":[288],"noise":[291,306,309],"signal.":[295],"So":[296,316],"considering":[297],"pulse":[302],"train":[303],"no":[305,311],"white":[308,457],"periodicity":[312],"suitable.":[315],"more":[318,343],"suitable":[319],"represent":[321,401],"by":[325],"one":[326],"parameter,":[328],"but":[329],"mixed-excitation":[332],"technique.":[333],"our":[335],"proposed":[336],"approach,":[337],"detailed":[344],"set,":[347],"order":[349],"increase":[351],"output":[353],"include":[360],"each":[363,385],"band":[364,386],"an":[367],"MBE":[368],"(Multi-Band":[369],"Excitation)":[370],"[3],":[372],"bandwidth":[376],"divided":[378],"into":[379,490],"number":[381,408],"sub-bands,":[383],"marked":[388],"unvoiced.":[393],"instead":[395],"mel-cepstral":[398],"coefficients":[399],"envelop,":[403],"fixed":[407],"which":[413],"modeled":[415],"models.":[420],"[4][5][6].":[447],"While":[448],"filtered":[456],"noise.":[458],"modified":[462,534],"language.":[470],"has":[472],"problem":[474],"diacretization,":[476],"text":[479,489],"should":[480],"be":[481,484],"diacretized":[482],"able":[485],"convert":[487],"sequence.":[492],"language":[495,503],"analysis":[496,504],"diacretization":[498],"RDI\u00ae":[502],"tools":[505],"Arabic,":[507],"out":[510],"scope":[512],"paper.":[515],"following":[518],"sections,":[519],"presented":[528,543,550],"section":[530,539,545,552],"2,":[531],"3.":[540],"Results":[541],"4,":[546],"conclusion":[548],"5.":[553],"Figure":[554]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}