{"id":"https://openalex.org/W234770729","doi":"https://doi.org/10.21437/icslp.1998-17","title":"Analytic generation of synthesis units by closed loop training for totally speaker driven text to speech system (TOS drive TTS)","display_name":"Analytic generation of synthesis units by closed loop training for totally speaker driven text to speech system (TOS drive TTS)","publication_year":1998,"publication_date":"1998-11-30","ids":{"openalex":"https://openalex.org/W234770729","doi":"https://doi.org/10.21437/icslp.1998-17","mag":"234770729"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.1998-17","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1998-17","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","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/A5112250968","display_name":"Masami Akamine","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masami Akamine","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5001471443","display_name":"Takehiko Kagoshima","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takehiko Kagoshima","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":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"paper 0139","last_page":"0"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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":0.9986000061035156,"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/T11309","display_name":"Music and Audio Processing","score":0.9929999709129333,"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/T12031","display_name":"Speech and dialogue systems","score":0.9922999739646912,"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/concatenation","display_name":"Concatenation (mathematics)","score":0.9299719333648682},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.920604407787323},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7503618001937866},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6632036566734314},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.60072922706604},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5313582420349121},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4923497438430786},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4816826283931732},{"id":"https://openalex.org/keywords/closed-loop","display_name":"Closed loop","score":0.4286927878856659},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.14354678988456726},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1409587860107422},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1049843430519104},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06100630760192871}],"concepts":[{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.9299719333648682},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.920604407787323},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7503618001937866},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6632036566734314},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.60072922706604},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5313582420349121},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4923497438430786},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4816826283931732},{"id":"https://openalex.org/C3019251811","wikidata":"https://www.wikidata.org/wiki/Q5135346","display_name":"Closed loop","level":2,"score":0.4286927878856659},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.14354678988456726},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1409587860107422},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1049843430519104},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06100630760192871},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/icslp.1998-17","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1998-17","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W33683307","https://openalex.org/W223646659","https://openalex.org/W1865819098","https://openalex.org/W2111953469","https://openalex.org/W2119085432","https://openalex.org/W2150716994","https://openalex.org/W2159219421"],"related_works":["https://openalex.org/W2588431733","https://openalex.org/W2391796527","https://openalex.org/W2387179309","https://openalex.org/W2388979876","https://openalex.org/W4245668640","https://openalex.org/W2032960563","https://openalex.org/W2142993035","https://openalex.org/W2899044948","https://openalex.org/W205537210","https://openalex.org/W2161566404"],"abstract_inverted_index":{"This":[0],"paper":[1],"provides":[2],"a":[3,61,91,100,115],"new":[4],"method":[5,68],"for":[6],"automatically":[7],"generating":[8],"speech":[9,54,58,63,80,112],"synthesis":[10,34,72,82,120],"units.":[11,121],"The":[12,44,66],"algorithm,":[13],"called":[14],"Closed-Loop":[15],"Training":[16],"(CLT),":[17],"is":[18,46,88,99],"based":[19,94],"on":[20],"evaluating":[21],"and":[22,56,109],"reducing":[23],"the":[24,50,71,105],"distortion":[25,31,45],"in":[26,40,60],"synthesized":[27,53],"speech.":[28],"It":[29],"minimizes":[30],"caused":[32],"by":[33,48],"process":[35],"such":[36],"as":[37],"prosodic":[38],"modification":[39],"an":[41],"analytic":[42],"way.":[43],"measured":[47],"calculating":[49],"error":[51],"between":[52],"units":[55,59,73],"natural":[57,79],"large":[62],"database":[64],"(corpus).":[65],"CLT":[67,87],"effectively":[69],"generates":[70,107],"that":[74],"are":[75],"most":[76],"resembling":[77],"of":[78,119],"after":[81],"process.":[83],"In":[84],"this":[85],"paper,":[86],"applied":[89],"to":[90],"waveform":[92],"concatenation":[93],"synthesizer,":[95],"whose":[96],"basic":[97],"unit":[98],"diphone.":[101],"By":[102],"using":[103],"CLT,":[104],"synthesizer":[106],"clear":[108],"smooth":[110],"synthetic":[111],"even":[113],"with":[114],"relatively":[116],"small":[117],"volume":[118]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
