{"id":"https://openalex.org/W172286355","doi":"https://doi.org/10.21437/interspeech.2009-593","title":"Feedback loop for prosody prediction in concatenative speech synthesis","display_name":"Feedback loop for prosody prediction in concatenative speech synthesis","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W172286355","doi":"https://doi.org/10.21437/interspeech.2009-593","mag":"172286355"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-593","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-593","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","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/A5071418947","display_name":"Javier Latorre","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127366","display_name":"Toshiba (South Korea)","ror":"https://ror.org/02mavrn48","country_code":"KR","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210127366"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Javier Latorre","raw_affiliation_strings":["Toshiba,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba,","institution_ids":["https://openalex.org/I4210127366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034915196","display_name":"Sergio Gracia","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127366","display_name":"Toshiba (South Korea)","ror":"https://ror.org/02mavrn48","country_code":"KR","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210127366"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sergio Gracia","raw_affiliation_strings":["Toshiba,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba,","institution_ids":["https://openalex.org/I4210127366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112250968","display_name":"Masami Akamine","orcid":null},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Masami Akamine","raw_affiliation_strings":["Polytechnic University of Catalonia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Polytechnic University of Catalonia","institution_ids":["https://openalex.org/I9617848"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2067","last_page":"2070"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9916999936103821,"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":0.9898999929428101,"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/prosody","display_name":"Prosody","score":0.937732458114624},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6283704042434692},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5990918874740601},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5960561633110046},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5334705710411072},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4296719431877136},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28859513998031616},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1246928870677948}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.937732458114624},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6283704042434692},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5990918874740601},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5960561633110046},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5334705710411072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4296719431877136},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28859513998031616},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1246928870677948}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2009-593","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-593","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W113106864","https://openalex.org/W234770729","https://openalex.org/W1927421023","https://openalex.org/W1935012542","https://openalex.org/W1976364128","https://openalex.org/W2004687614","https://openalex.org/W2093094447","https://openalex.org/W2111194146","https://openalex.org/W2127530508","https://openalex.org/W2151416040","https://openalex.org/W2287489159"],"related_works":["https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W3149582125","https://openalex.org/W1984347656","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W152045069","https://openalex.org/W652196294","https://openalex.org/W2368700418"],"abstract_inverted_index":{"Abstract":[0],"We":[1],"propose":[2],"a":[3,12,52,80],"method":[4,32,50],"for":[5],"concatenative":[6],"speech":[7,148],"synthesis":[8],"thatpermits":[9],"to":[10,72,108],"obtain":[11,122],"better":[13],"matching":[14],"between":[15,131],"the":[16,22,26,55,58,63,67,86,92,97,109,111,115,123,128,132,139,143],"logF0":[17,95],"and":[18,25,41,46,89,94,138],"dura-tion":[19],"predicted":[20],"by":[21,103,135,142],"prosody":[23,59,74,112,124,144],"module":[24,60],"waveform":[27],"genera-tion":[28],"back-end.":[29],"The":[30,49,76,100],"proposed":[31],"is":[33,70,106],"based":[34],"upon":[35],"our":[36],"previousmultilevel":[37],"parametric":[38,151],"F0":[39,136],"model":[40,82,105],"Toshiba\u2019s":[42],"plural":[43],"unit":[44],"selec-tion":[45],"fusion":[47],"synthesizer.":[48],"adds":[51],"feedback":[53,77],"loopfrom":[54],"back-end":[56],"into":[57],"so":[61],"that":[62,126],"prosod-ical":[64],"information":[65],"of":[66,85,91,96,117],"selected":[68,98],"units":[69],"used":[71],"re-estimatenew":[73],"values.":[75],"loop":[78],"de\ufb01nes":[79],"frame-levelprosody":[81],"which":[83],"consists":[84],"average":[87],"value":[88],"vari-ance":[90],"duration":[93],"units.":[99],"log-likelihood":[101,156],"de\ufb01ned":[102],"this":[104,118],"added":[107],"log-likelihoodof":[110],"model.":[113],"From":[114],"maximization":[116],"total":[119],"log-likelihood,":[120],"we":[121],"values":[125],"produce":[127],"opti-mum":[129],"compromise":[130],"distortion":[133],"introduced":[134],"dis-continuities":[137],"one":[140],"created":[141],"adjusting":[145],"signalprocessing.Index":[146],"Terms:":[147],"synthesis,":[149],"multilevel,":[150],"F0,prosody,":[152],"Discrete":[153],"cosine":[154],"transform,":[155],"maximiza-tion":[157]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}