{"id":"https://openalex.org/W185519286","doi":"https://doi.org/10.21437/interspeech.2008-179","title":"Statistical text-to-speech synthesis with improved dynamics","display_name":"Statistical text-to-speech synthesis with improved dynamics","publication_year":2008,"publication_date":"2008-09-22","ids":{"openalex":"https://openalex.org/W185519286","doi":"https://doi.org/10.21437/interspeech.2008-179","mag":"185519286"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2008-179","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","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/A5046771851","display_name":"Stas Tiomkin","orcid":"https://orcid.org/0000-0003-3677-6874"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Stas Tiomkin","raw_affiliation_strings":["TECHNION-Israel Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TECHNION-Israel Institute of Technology","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009813683","display_name":"D. Malah","orcid":"https://orcid.org/0009-0001-8310-7844"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"David Malah","raw_affiliation_strings":["TECHNION-Israel Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TECHNION-Israel Institute of Technology","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I174306211"],"apc_list":null,"apc_paid":null,"fwci":0.2518,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.41419618,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1841","last_page":"1844"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9973000288009644,"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":0.9973000288009644,"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":0.9753999710083008,"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":0.9642999768257141,"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/computer-science","display_name":"Computer science","score":0.7577229738235474},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7147029042243958},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7106045484542847},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6883098483085632},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6133229732513428},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.6055024862289429},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5640318393707275},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49650031328201294},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4880012571811676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4569341540336609},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4474937915802002},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.41451945900917053},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41216757893562317},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38929641246795654},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1792987585067749},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09667432308197021},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.07067713141441345}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7577229738235474},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7147029042243958},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7106045484542847},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6883098483085632},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6133229732513428},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.6055024862289429},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5640318393707275},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49650031328201294},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4880012571811676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4569341540336609},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4474937915802002},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.41451945900917053},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41216757893562317},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38929641246795654},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1792987585067749},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09667432308197021},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.07067713141441345},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2008-179","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W75668230","https://openalex.org/W1514737389","https://openalex.org/W2154920538"],"related_works":["https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W1909292483","https://openalex.org/W1428730622","https://openalex.org/W1658560081","https://openalex.org/W2146616055","https://openalex.org/W2899676847","https://openalex.org/W596245619","https://openalex.org/W2254895521"],"abstract_inverted_index":{"In":[0,87],"statistical":[1],"TTS":[2],"systems":[3],"(STTS),":[4],"speech":[5,39,133],"features":[6],"dynamics":[7,26,33,50,71,94,111],"is":[8,60,95],"modeled":[9],"by":[10],"firstand":[11],"second-order":[12],"feature":[13,25,49,70,82,93],"frame":[14,22,24],"differences,":[15],"which,":[16],"typically,":[17],"do":[18],"not":[19],"satisfactorily":[20],"represent":[21],"to":[23,77,107,140],"present":[27],"in":[28,35,98],"natural":[29,113],"speech.":[30,46,114],"The":[31],"reduced":[32],"results":[34],"over":[36],"smoothing":[37],"of":[38,81,100,112,135],"features,":[40],"often":[41],"sounding":[42],"as":[43],"muffled":[44],"synthesized":[45,132],"To":[47,115],"improve":[48],"a":[51,65,85,117,122],"Global":[52],"Variance":[53],"approach":[54,67],"has":[55],"been":[56],"suggested.":[57],"However,":[58],"it":[59],"computationally":[61],"complex.":[62],"We":[63],"propose":[64,121],"different":[66],"for":[68,124],"modeling":[69],"based":[72],"on":[73],"applying":[74],"the":[75,78,88,91,110,127],"DFT":[76],"whole":[79,118],"set":[80],"frames":[83],"representing":[84],"phoneme.":[86],"transform":[89],"domain":[90],"inter-frame":[92],"then":[96],"expressed":[97],"terms":[99],"inter-harmonic":[101],"content,":[102],"which":[103,130],"can":[104],"be":[105],"modified":[106],"statistically":[108],"match":[109],"synthesize":[116],"utterance":[119],"we":[120],"method":[123],"smoothly":[125],"combining":[126],"enhanced-dynamics":[128],"phonemes,":[129],"improves":[131],"quality":[134],"STTS":[136],"with":[137],"similar":[138],"complexity":[139],"conventional":[141],"STTS.":[142]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
