{"id":"https://openalex.org/W51508392","doi":null,"title":"Text to Speech Synthesis: New Paradigms and Advances","display_name":"Text to Speech Synthesis: New Paradigms and Advances","publication_year":2004,"publication_date":"2004-08-03","ids":{"openalex":"https://openalex.org/W51508392","mag":"51508392"},"language":"en","primary_location":{"id":"pmh:oai:aleph.bib-bvb.de:BVB01-012907966","doi":null,"is_oa":false,"landing_page_url":"http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=012907966&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5104114055","display_name":"Shrikanth S. Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204","observed_orcids":["https://orcid.org/0000-0002-1052-6204"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112421995","display_name":"Abeer A. Alwan","orcid":"https://orcid.org/0000-0003-3390-9379","observed_orcids":["https://orcid.org/0000-0003-3390-9379"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abeer Alwan","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":4.8944,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.94939003,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":98},"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":0.9994999766349792,"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":0.9994999766349792,"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":0.00019999999494757503,"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/T10403","display_name":"Phonetics and Phonology Research","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/text-to-speech","display_name":"text-to-speech","score":0.972000002861023},{"id":"https://openalex.org/keywords/corpus-based-speech-synthesis","display_name":"corpus-based speech synthesis","score":0.8460000157356262},{"id":"https://openalex.org/keywords/unit-selection","display_name":"unit selection","score":0.8050000071525574},{"id":"https://openalex.org/keywords/articulatory-modeling","display_name":"articulatory modeling","score":0.8130000233650208},{"id":"https://openalex.org/keywords/concatenative-synthesis","display_name":"concatenative synthesis","score":0.8320000171661377},{"id":"https://openalex.org/keywords/pitch-modification","display_name":"pitch modification","score":0.9449999928474426},{"id":"https://openalex.org/keywords/multilingual-speech-synthesis","display_name":"multilingual speech synthesis","score":0.9580000042915344},{"id":"https://openalex.org/keywords/japanese-prosody","display_name":"Japanese prosody","score":0.7080000042915344},{"id":"https://openalex.org/keywords/expressive-speech","display_name":"expressive speech","score":0.777999997138977},{"id":"https://openalex.org/keywords/prosody-control","display_name":"prosody control","score":0.45399999618530273},{"id":"https://openalex.org/keywords/mbrola","display_name":"MBROLA","score":0.578000009059906},{"id":"https://openalex.org/keywords/spectral-distance","display_name":"spectral distance","score":0.32600000500679016}],"concepts":[{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7755256295204163},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7261368632316589},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5946993231773376},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.5223556756973267},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.513652503490448},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.42059171199798584},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38696929812431335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36924469470977783},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3410780131816864},{"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":"pmh:oai:aleph.bib-bvb.de:BVB01-012907966","doi":null,"is_oa":false,"landing_page_url":"http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=012907966&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:51508392","doi":null,"is_oa":false,"landing_page_url":"http://ci.nii.ac.jp/ncid/BA6962020X","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2102737569","https://openalex.org/W2407840102","https://openalex.org/W642254059","https://openalex.org/W1986272181","https://openalex.org/W2263694371","https://openalex.org/W604781219","https://openalex.org/W2533081766","https://openalex.org/W2424907262","https://openalex.org/W2031807157","https://openalex.org/W2216757598"],"abstract_inverted_index":{"Preface.":[0],"Foreword.":[1],"1.":[2],"Reducing":[3],"Discontinuities":[4],"at":[5],"Synthesis":[6,206,256,285,312],"Time":[7],"for":[8,79,369],"Corpus-Based":[9],"Speech":[10,49,82,111,142,153,167,171,179,193,205,263,284,288,363],"Synthesis.":[11,31,83,112,130,143,172,183,194],"Baris":[12],"Bozkurt,":[13],"Thierry":[14],"Dutoit,":[15],"Romain":[16,319],"Prudon,":[17,320],"Christophe":[18,321],"D'Alessandro":[19,322],"and":[20,34,53,86,98,116,149,175,199,238,266,273,305,323,349],"Vincent":[21],"Pagel.":[22],"Introduction.":[23,56,89,120,152,178,203,241,276,328,353],"Shift-Only":[24],"F0":[25,208],"Smoothing.":[26],"Improving":[27],"Quality":[28,39,62,71],"of":[29,45,60,65,69,125,138,166,243,278,281,293,297,313,374],"MBROLA":[30],"Evaluation.":[32,334],"Discussions":[33],"Conclusion.":[35,161,223,302,336],"Bibliography.":[36,75,101,133,162,186,224,259,308,337,382],"2.":[37],"Voice":[38,61,70],"Variation":[40],"in":[41,107,141,170,182],"a":[42,46],"Long-Term":[43],"Recording":[44],"Single":[47],"Speaker":[48],"Corpus.":[50],"Hisashi":[51],"Kawai":[52],"Minoru":[54],"Tsuzaki.":[55],"Perceptual":[57,94,159],"Experiment.":[58,160],"Factors":[59],"Variation.":[63],"Candidates":[64],"Acoustic":[66],"Correlates.":[67],"Prediction":[68],"Difference":[72],"Scores.":[73],"Summary.":[74],"3.":[76],"Join":[77],"Cost":[78],"Unit":[80,310],"Selection":[81,311],"Jithendra":[84],"Vepa":[85],"Simon":[87],"King.":[88],"Previous":[90],"Work.":[91],"Spectral":[92],"Distances.":[93],"Listening":[95],"Tests.":[96],"Results":[97,298],"Discussion.":[99,222],"Conclusions.":[100,258,381],"4.":[102],"Articulatory":[103,121,129],"Modeling:":[104],"A":[105,354],"Role":[106],"Concatenative":[108,128],"Text":[109,156],"to":[110,191],"M.":[113],"Mohan":[114],"Sondhi":[115],"Daniel":[117],"J.":[118],"Sinder.":[119],"Modeling.":[122],"Rule-Based":[123,367],"Control":[124,227],"the":[126,250],"Parameters.":[127],"Concluding":[131],"Remarks.":[132],"5.":[134],"Minimizing":[135],"The":[136,164],"Amount":[137],"Pitch":[139],"Modification":[140],"Esther":[144],"Klabbers,":[145],"Jan":[146],"van":[147],"Santen":[148],"Johan":[150],"Wouters.":[151],"Corpus":[154,157],"Analysis.":[155,158],"6.":[163],"Use":[165,373],"Recognition":[168],"Technology":[169],"Mari":[173],"Ostendorf":[174],"Ivan":[176],"Bulyko.":[177],"Recognition.":[180],"ASR":[181],"Limitations.":[184],"Speculations.":[185],"7.":[187],"An":[188],"HMM-Based":[189,204,229,244],"Approach":[190],"Multilingual":[192],"Keiichi":[195],"Tokuda,":[196],"Heiga":[197],"Zen":[198],"Alan":[200],"W.":[201],"Black.":[202],"System.":[207,246,378],"Pattern":[209],"Modeling":[210],"by":[211,331],"HMM.":[212,217],"Speech-Parameter":[213],"Generation":[214,248],"from":[215],"an":[216,375],"Implementation":[218],"on":[219],"Festival":[220],"Architecture.":[221],"8.":[225],"Prosody":[226,247,330],"For":[228,357],"Japanese":[230],"TTS.":[231],"Koji":[232],"Iwano,":[233],"Masahiro":[234],"Yamada,":[235],"Taro":[236],"Togawa":[237],"Sadaoki":[239],"Furui.":[240],"Outline":[242],"TTS":[245,377],"Using":[249,316],"Quantification":[251],"Theory":[252],"(Type":[253],"1).":[254],"Speech-Rate-Variable":[255],"Method.":[257],"9.":[260],"Synthesizing":[261],"Expressive":[262,294,340,359,362,371,376],"Overview:":[264],"Challenges,":[265],"Open":[267,303],"Questions.":[268],"Murtaza":[269],"Bulut,":[270],"Shrikanth":[271],"Narayanan":[272],"Lewis":[274],"Johnson.":[275],"Theories":[277],"Emotion.":[279],"Dimensions":[280],"Emotional":[282,287],"Space.":[283],"Methods.":[286],"Data":[289],"Collection.":[290],"Experimental":[291],"Evaluation":[292,315],"Speech.":[295,342,360,372],"Presentation":[296],"From":[299],"Case":[300],"Studies.":[301],"Questions":[304],"Future":[306],"Directions.":[307],"10.":[309],"Prosody:":[314],"Diphone":[317],"Transplantation.":[318],"Philippe":[324],"Boula":[325],"de":[326],"Mareuil.":[327],"Computing":[329],"Selection.":[332],"Comparative":[333],"Results.":[335],"11.":[338],"Toward":[339],"Synthetic":[341],"Ellen":[343],"Eide,":[344],"Raimo":[345],"Bakis,":[346],"Wael":[347],"Hamza":[348],"John":[350],"F.":[351],"Pitrelli.":[352],"Pilot":[355],"Study":[356],"Generating":[358,361,370],"with":[364],"Limited":[365],"Resources.":[366],"Methods":[368],"Assessing":[379],"Performance.":[380],"Footnotes.":[383],"Copyright":[384],"Forms.":[385],"References.":[386],"Index.":[387]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2016-06-24T00:00:00"}