{"id":"https://openalex.org/W2157273572","doi":"https://doi.org/10.1109/icassp.2008.4518522","title":"On the state definition for a trainable excitation model in HMM-based speech synthesis","display_name":"On the state definition for a trainable excitation model in HMM-based speech synthesis","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2157273572","doi":"https://doi.org/10.1109/icassp.2008.4518522","mag":"2157273572"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518522","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://naist.repo.nii.ac.jp/records/4639","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110289715","display_name":"Ranniery Maia","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"R. Maia","raw_affiliation_strings":["ATR Spoken Language Communication Research Laboratories, Japan","Technology (NICT), National Institute of Information and Communications Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ATR Spoken Language Communication Research Laboratories, Japan","institution_ids":[]},{"raw_affiliation_string":"Technology (NICT), National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]},{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"T. Toda","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan","Technology (NICT), National Institute of Information and Communications Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Technology (NICT), National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103023678","display_name":"Keiichi Tokuda","orcid":"https://orcid.org/0000-0001-6143-0133"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]},{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"K. Tokuda","raw_affiliation_strings":["Nagoya Institute of Technology, Japan","Technology (NICT), National Institute of Information and Communications Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Technology (NICT), National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110187456","display_name":"S. Sakai","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"S. Sakai","raw_affiliation_strings":["ATR Spoken Language Communication Research Laboratories, Japan","Technology (NICT), National Institute of Information and Communications Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ATR Spoken Language Communication Research Laboratories, Japan","institution_ids":[]},{"raw_affiliation_string":"Technology (NICT), National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"S. Nakamura","raw_affiliation_strings":["ATR Spoken Language Communication Research Laboratories, Japan","Technology (NICT), National Institute of Information and Communications Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ATR Spoken Language Communication Research Laboratories, Japan","institution_ids":[]},{"raw_affiliation_string":"Technology (NICT), National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9358,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.85266873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3965","last_page":"3968"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T12031","display_name":"Speech and dialogue systems","score":0.9957000017166138,"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":0.9940999746322632,"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/naturalness","display_name":"Naturalness","score":0.8680596351623535},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8484362363815308},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.749611496925354},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.7085342407226562},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6236732602119446},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5723437070846558},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5539144277572632},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5427773594856262},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5365521907806396},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5040063261985779},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.45921632647514343},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4485366642475128},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.44583016633987427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.361849308013916},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.28001052141189575},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0660761296749115}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8680596351623535},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8484362363815308},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.749611496925354},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.7085342407226562},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6236732602119446},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5723437070846558},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5539144277572632},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5427773594856262},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5365521907806396},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5040063261985779},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.45921632647514343},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4485366642475128},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.44583016633987427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.361849308013916},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28001052141189575},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0660761296749115},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"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/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2008.4518522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518522","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01146:0005783090","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/4639","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"conference paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.210.5802","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.210.5802","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://spalab.naist.jp/~tomoki/Tomoki/Conferences/ICASSP2008_ClustExcitHTS.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01146:0005783090","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/4639","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"conference paper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W155946340","https://openalex.org/W200094172","https://openalex.org/W795690926","https://openalex.org/W1514941256","https://openalex.org/W1756939916","https://openalex.org/W2022554507","https://openalex.org/W2042691334","https://openalex.org/W2155498861","https://openalex.org/W2157273572","https://openalex.org/W2500358397","https://openalex.org/W6637893649"],"related_works":["https://openalex.org/W1914543332","https://openalex.org/W2108985546","https://openalex.org/W2038801705","https://openalex.org/W2077992636","https://openalex.org/W2279374969","https://openalex.org/W1537411440","https://openalex.org/W290673751","https://openalex.org/W2017702615","https://openalex.org/W2147186888","https://openalex.org/W2024201202"],"abstract_inverted_index":{"One":[0],"of":[1,4,16,23,44,47,95],"the":[2,13,17,21,38,42,55,93,96],"issues":[3],"speech":[5,25],"synthesizers":[6],"based":[7],"on":[8,87,107],"hidden":[9],"Markov":[10],"models":[11],"concerns":[12],"vocoded":[14],"quality":[15],"synthesized":[18],"speech.":[19],"From":[20],"principle":[22],"analysis-by-synthesis":[24],"coders":[26],"a":[27,45,51,77],"trainable":[28],"excitation":[29],"model":[30],"has":[31],"been":[32],"proposed":[33],"to":[34,53],"improve":[35],"naturalness,":[36],"where":[37],"method":[39,78],"consists":[40],"in":[41,50],"design":[43,113],"set":[46],"state-dependent":[48],"filters":[49],"way":[52],"minimize":[54],"distortion":[56],"between":[57],"residual":[58,97,108],"and":[59],"synthetic":[60],"excitation.":[61],"Although":[62],"this":[63],"approach":[64],"seems":[65],"successful,":[66],"state":[67,80],"definition":[68,81],"still":[69],"represents":[70],"an":[71],"open":[72],"issue.":[73],"This":[74],"paper":[75],"describes":[76],"for":[79],"wherein":[82],"bottom-up":[83],"clustering":[84],"is":[85],"performed":[86],"full":[88],"context":[89],"decision":[90],"trees,":[91],"using":[92],"likelihood":[94],"database":[98],"as":[99],"merging":[100],"criterion.":[101],"Experiments":[102],"have":[103],"shown":[104],"that":[105],"improvement":[106],"modeling":[109],"through":[110],"better":[111],"filter":[112],"can":[114],"be":[115],"achieved.":[116]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
