{"id":"https://openalex.org/W2064148454","doi":"https://doi.org/10.1109/icassp.2009.4960513","title":"Full covariance state duration modeling for HMM-based speech synthesis","display_name":"Full covariance state duration modeling for HMM-based speech synthesis","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2064148454","doi":"https://doi.org/10.1109/icassp.2009.4960513","mag":"2064148454"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960513","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960513","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 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://nitech.repo.nii.ac.jp/records/3453","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100618443","display_name":"Heng Lu","orcid":"https://orcid.org/0009-0009-9236-8825"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Lu","raw_affiliation_strings":["IFlytek Speech Laboratory, University of Science and Technology, Hefei, Anhui, China","iFlytek Speech Lab, University of Science and Technology of China, Hefei, Anhui, CHINA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IFlytek Speech Laboratory, University of Science and Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"iFlytek Speech Lab, University of Science and Technology of China, Hefei, Anhui, CHINA#TAB#","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039492028","display_name":"Yi-Jian Wu","orcid":null},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yi-Jian Wu","raw_affiliation_strings":["Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan","Department of Computer Science, Nagoya Institute of Technology, 466-8555 JAPAN#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, 466-8555 JAPAN#TAB#","institution_ids":["https://openalex.org/I197274945"]}]},{"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiichi Tokuda","raw_affiliation_strings":["Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan","Department of Computer Science, Nagoya Institute of Technology, 466-8555 JAPAN#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, 466-8555 JAPAN#TAB#","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-Rong Dai","raw_affiliation_strings":["IFlytek Speech Laboratory, University of Science and Technology, Hefei, Anhui, China","iFlytek Speech Lab, University of Science and Technology of China, Hefei, Anhui, CHINA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IFlytek Speech Laboratory, University of Science and Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"iFlytek Speech Lab, University of Science and Technology of China, Hefei, Anhui, CHINA#TAB#","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102734836","display_name":"Ren-Hua Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ren-Hua Wang","raw_affiliation_strings":["IFlytek Speech Laboratory, University of Science and Technology, Hefei, Anhui, China","iFlytek Speech Lab, University of Science and Technology of China, Hefei, Anhui, CHINA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IFlytek Speech Laboratory, University of Science and Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"iFlytek Speech Lab, University of Science and Technology of China, Hefei, Anhui, CHINA#TAB#","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9059,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.80560997,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4033","last_page":"4036"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9904999732971191,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9843999743461609,"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/covariance","display_name":"Covariance","score":0.750847578048706},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6981871724128723},{"id":"https://openalex.org/keywords/rational-quadratic-covariance-function","display_name":"Rational quadratic covariance function","score":0.6722480654716492},{"id":"https://openalex.org/keywords/covariance-matrix","display_name":"Covariance matrix","score":0.668272078037262},{"id":"https://openalex.org/keywords/cma-es","display_name":"CMA-ES","score":0.6302632093429565},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.627204954624176},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.575270414352417},{"id":"https://openalex.org/keywords/covariance-function","display_name":"Covariance function","score":0.5584579706192017},{"id":"https://openalex.org/keywords/covariance-intersection","display_name":"Covariance intersection","score":0.5414708852767944},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.529310405254364},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.483822762966156},{"id":"https://openalex.org/keywords/mat\u00e9rn-covariance-function","display_name":"Mat\u00e9rn covariance function","score":0.46333447098731995},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4353407025337219},{"id":"https://openalex.org/keywords/diagonal","display_name":"Diagonal","score":0.42192232608795166},{"id":"https://openalex.org/keywords/estimation-of-covariance-matrices","display_name":"Estimation of covariance matrices","score":0.4156542420387268},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3929577171802521},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32930052280426025},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.258359432220459},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10334470868110657}],"concepts":[{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.750847578048706},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6981871724128723},{"id":"https://openalex.org/C148893098","wikidata":"https://www.wikidata.org/wiki/Q7295778","display_name":"Rational quadratic covariance function","level":5,"score":0.6722480654716492},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.668272078037262},{"id":"https://openalex.org/C205555498","wikidata":"https://www.wikidata.org/wiki/Q505588","display_name":"CMA-ES","level":4,"score":0.6302632093429565},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.627204954624176},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.575270414352417},{"id":"https://openalex.org/C137250428","wikidata":"https://www.wikidata.org/wiki/Q5178897","display_name":"Covariance function","level":3,"score":0.5584579706192017},{"id":"https://openalex.org/C83042196","wikidata":"https://www.wikidata.org/wiki/Q5178898","display_name":"Covariance intersection","level":4,"score":0.5414708852767944},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.529310405254364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.483822762966156},{"id":"https://openalex.org/C118006245","wikidata":"https://www.wikidata.org/wiki/Q6792079","display_name":"Mat\u00e9rn covariance function","level":5,"score":0.46333447098731995},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4353407025337219},{"id":"https://openalex.org/C130367717","wikidata":"https://www.wikidata.org/wiki/Q189791","display_name":"Diagonal","level":2,"score":0.42192232608795166},{"id":"https://openalex.org/C180877172","wikidata":"https://www.wikidata.org/wiki/Q5401390","display_name":"Estimation of covariance matrices","level":3,"score":0.4156542420387268},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3929577171802521},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32930052280426025},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.258359432220459},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10334470868110657},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2009.4960513","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960513","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01154:0001435320","is_oa":true,"landing_page_url":"https://nitech.repo.nii.ac.jp/records/3453","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2009. IEEE International Conference on Acoustics, Speech and Signal Processing, 2009.","raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01154:0001435320","is_oa":true,"landing_page_url":"https://nitech.repo.nii.ac.jp/records/3453","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2009. IEEE International Conference on Acoustics, Speech and Signal Processing, 2009.","raw_type":"conference paper"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W36786594","https://openalex.org/W1563645159","https://openalex.org/W1600722501","https://openalex.org/W1963627370","https://openalex.org/W2042691334","https://openalex.org/W2154920538","https://openalex.org/W2158069733","https://openalex.org/W2166823384","https://openalex.org/W3036214897","https://openalex.org/W3217250306","https://openalex.org/W4301420498","https://openalex.org/W6633741279","https://openalex.org/W6779356719","https://openalex.org/W6804310723"],"related_works":["https://openalex.org/W2126916073","https://openalex.org/W2022823194","https://openalex.org/W2138094255","https://openalex.org/W2572601863","https://openalex.org/W341081156","https://openalex.org/W1999545733","https://openalex.org/W3138022501","https://openalex.org/W3000630362","https://openalex.org/W4287906493","https://openalex.org/W2104432942"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,19],"state":[4,40,50,72],"duration":[5,41,73],"modeling":[6],"method":[7,81],"using":[8,54,70],"full":[9,20,60],"covariance":[10,21,28,61],"matrix":[11,22,29],"for":[12],"HMM-based":[13],"speech":[14,69],"synthesis.":[15],"In":[16],"this":[17],"method,":[18],"instead":[23],"of":[24,42,88],"the":[25,33,39,49,55,67,79,85],"conventional":[26,80],"diagonal":[27],"is":[30,75],"adopted":[31],"in":[32],"multi-dimensional":[34],"Gaussian":[35],"distribution":[36],"to":[37],"model":[38],"each":[43],"context-dependent":[44,57],"phoneme.":[45],"At":[46],"synthesis":[47],"stage,":[48],"durations":[51],"are":[52],"predicted":[53],"clustered":[56],"distributions":[58],"with":[59],"matrices.":[62],"Experimental":[63],"results":[64],"show":[65],"that":[66],"synthesized":[68,89],"full-covariance":[71],"models":[74],"more":[76],"natural":[77],"than":[78],"when":[82],"we":[83],"change":[84],"speaking":[86],"rate":[87],"speech.":[90]},"counts_by_year":[{"year":2020,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}