{"id":"https://openalex.org/W2120514051","doi":"https://doi.org/10.1109/icassp.2009.4960510","title":"A polynomial segment model based statistical parametric speech synthesis sytem","display_name":"A polynomial segment model based statistical parametric speech synthesis sytem","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2120514051","doi":"https://doi.org/10.1109/icassp.2009.4960510","mag":"2120514051"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960510","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960510","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024963902","display_name":"Jingwei Sun","orcid":"https://orcid.org/0000-0001-8358-9487"},"institutions":[{"id":"https://openalex.org/I4210099903","display_name":"Nokia (China)","ror":"https://ror.org/01607kg94","country_code":"CN","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I4210099903"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jingwei Sun","raw_affiliation_strings":["Nokia Research Center, Beijing, China","Thinkit Speech Laboratory, Institute of Acoustics, Chinese Academy and Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Nokia Research Center, Beijing, China","institution_ids":["https://openalex.org/I4210099903"]},{"raw_affiliation_string":"Thinkit Speech Laboratory, Institute of Acoustics, Chinese Academy and Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100637638","display_name":"Feng Ding","orcid":"https://orcid.org/0000-0002-2721-2025"},"institutions":[{"id":"https://openalex.org/I4210099903","display_name":"Nokia (China)","ror":"https://ror.org/01607kg94","country_code":"CN","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I4210099903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Ding","raw_affiliation_strings":["Nokia Research Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Nokia Research Center, Beijing, China","institution_ids":["https://openalex.org/I4210099903"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110643362","display_name":"Yahui Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099903","display_name":"Nokia (China)","ror":"https://ror.org/01607kg94","country_code":"CN","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I4210099903"]},{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yahui Wu","raw_affiliation_strings":["Nokia Research Center, Beijing, China","School of Information Engineering, University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Nokia Research Center, Beijing, China","institution_ids":["https://openalex.org/I4210099903"]},{"raw_affiliation_string":"School of Information Engineering, University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5024963902"],"corresponding_institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I4210099903"],"apc_list":null,"apc_paid":null,"fwci":0.8724,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.80644963,"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":"4021","last_page":"4024"},"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":0.9900000095367432,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9855999946594238,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.7355512976646423},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7103005051612854},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6727989912033081},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6589633822441101},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.5925086140632629},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5822771787643433},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.48050034046173096},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.45192596316337585},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3347667455673218},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3120202422142029},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15582919120788574}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7355512976646423},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7103005051612854},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6727989912033081},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6589633822441101},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.5925086140632629},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5822771787643433},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.48050034046173096},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.45192596316337585},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3347667455673218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3120202422142029},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15582919120788574},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2009.4960510","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960510","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W175280642","https://openalex.org/W204428907","https://openalex.org/W1600722501","https://openalex.org/W1846837356","https://openalex.org/W2083393647","https://openalex.org/W2145564828","https://openalex.org/W2145575463","https://openalex.org/W2154920538","https://openalex.org/W2166305974","https://openalex.org/W2167845555","https://openalex.org/W2296704011","https://openalex.org/W3142087749","https://openalex.org/W4301420498","https://openalex.org/W4395452447","https://openalex.org/W6680886407","https://openalex.org/W6681402030","https://openalex.org/W6684496986"],"related_works":["https://openalex.org/W4324119469","https://openalex.org/W4391272374","https://openalex.org/W2164868312","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2160650576","https://openalex.org/W2433276473"],"abstract_inverted_index":{"In":[0,47],"this":[1,48],"paper,":[2],"we":[3],"present":[4],"a":[5,36,68],"statistical":[6],"parametric":[7],"speech":[8,25,37,92,102,140],"synthesis":[9],"system":[10,145],"based":[11],"on":[12,107],"the":[13,21,30,33,41,45,60,96,112,115,121,138,148],"polynomial":[14],"segment":[15,64,98],"model":[16,80],"(PSM).":[17],"As":[18],"one":[19],"of":[20,32,44,114,137,151],"segmental":[22],"models":[23],"for":[24,62,79],"signals,":[26],"PSM":[27,129],"explicitly":[28],"describes":[29],"trajectory":[31],"features":[34],"in":[35,147],"segment,":[38],"and":[39,51,111,135],"keeps":[40],"internal":[42],"dynamics":[43],"segment.":[46],"work,":[49],"spectral":[50],"excitation":[52],"parameters":[53,93],"are":[54,87],"modeled":[55,66],"by":[56,67],"PSMs":[57,86],"simultaneously,":[58],"while":[59],"duration":[61],"each":[63],"is":[65,77,105,118,146],"single":[69],"Gaussian":[70],"distribution.":[71],"A":[72],"top-down":[73],"K-means":[74],"clustering":[75],"technique":[76],"applied":[78],"tying.":[81],"Mean":[82],"trajectories":[83],"acquired":[84],"from":[85],"used":[88],"directly":[89],"to":[90,95],"generate":[91],"according":[94],"estimated":[97],"duration.":[99],"An":[100],"English":[101],"synthesizer":[103],"back-end":[104],"implemented":[106],"CMU":[108],"Arctic":[109],"corpus":[110],"performance":[113],"new":[116],"approach":[117],"compared":[119],"with":[120],"classical":[122],"HMM-based":[123],"one.":[124],"Experimental":[125],"results":[126],"show":[127],"that":[128],"modeling":[130],"can":[131],"achieve":[132],"similar":[133],"naturalness":[134],"intelligence":[136],"synthetic":[139],"as":[141],"HMM":[142],"modeling.":[143],"The":[144],"early":[149],"stage":[150],"its":[152],"development.":[153]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}