{"id":"https://openalex.org/W2135707066","doi":"https://doi.org/10.1109/tasl.2009.2014796","title":"Integrating Articulatory Features Into HMM-Based Parametric Speech Synthesis","display_name":"Integrating Articulatory Features Into HMM-Based Parametric Speech Synthesis","publication_year":2009,"publication_date":"2009-06-25","ids":{"openalex":"https://openalex.org/W2135707066","doi":"https://doi.org/10.1109/tasl.2009.2014796","mag":"2135707066"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2009.2014796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2009.2014796","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/84b37979-95f8-41d1-9a08-f4fa96826096","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"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"]},{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["iFlytek Speech Laboratory, University of Science and Technology, Hefei, China","iFlytek Speech Lab., Univ. of Sci. & Technol. of China, Hefei"],"affiliations":[{"raw_affiliation_string":"iFlytek Speech Laboratory, University of Science and Technology, Hefei, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I16365422"]},{"raw_affiliation_string":"iFlytek Speech Lab., Univ. of Sci. & Technol. of China, Hefei","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055415493","display_name":"Korin Richmond","orcid":"https://orcid.org/0000-0003-1450-8270"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Korin Richmond","raw_affiliation_strings":["Center of Speech Technology Research (CSTR), University of Edinburgh, Edinburgh, UK","Center for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"Center of Speech Technology Research (CSTR), University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Center for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["Center of Speech Technology Research (CSTR), University of Edinburgh, Edinburgh, UK","Center for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"Center of Speech Technology Research (CSTR), University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Center for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"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"]},{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ren-Hua Wang","raw_affiliation_strings":["iFlytek Speech Laboratory, University of Science and Technology, Hefei, China","iFlytek Speech Lab., Univ. of Sci. & Technol. of China, Hefei"],"affiliations":[{"raw_affiliation_string":"iFlytek Speech Laboratory, University of Science and Technology, Hefei, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I16365422"]},{"raw_affiliation_string":"iFlytek Speech Lab., Univ. of Sci. & Technol. of China, Hefei","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059767940"],"corresponding_institution_ids":["https://openalex.org/I126520041","https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":10.3617,"has_fulltext":true,"cited_by_count":107,"citation_normalized_percentile":{"value":0.98302689,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"17","issue":"6","first_page":"1171","last_page":"1185"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9966999888420105,"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":0.9951000213623047,"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":0.8051373958587646},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7789148092269897},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.695220410823822},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.678777277469635},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.663493275642395},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5413020253181458},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5245221853256226},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5221386551856995},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.49586233496665955},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3587382137775421},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35656633973121643},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11232852935791016}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8051373958587646},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7789148092269897},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.695220410823822},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.678777277469635},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.663493275642395},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5413020253181458},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5245221853256226},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5221386551856995},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.49586233496665955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3587382137775421},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35656633973121643},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11232852935791016},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tasl.2009.2014796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2009.2014796","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/84b37979-95f8-41d1-9a08-f4fa96826096","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/84b37979-95f8-41d1-9a08-f4fa96826096","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ling, Z-H, Richmond, K, Yamagishi, J & Wang, R-H 2009, 'Integrating Articulatory Features Into HMM-Based Parametric Speech Synthesis', IEEE Transactions on Audio, Speech and Language Processing, vol. 17, no. 6, pp. 1171-1851. https://doi.org/10.1109/TASL.2009.2014796","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:era.ed.ac.uk:1842/3912","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/3912","pdf_url":"https://era.ed.ac.uk/bitstream/1842/3912/1/05109768.pdf","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.704.7245","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.704.7245","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://staff.ustc.edu.cn/%7Ezhling/paper/Ling_TASLP_2009.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/84b37979-95f8-41d1-9a08-f4fa96826096","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/84b37979-95f8-41d1-9a08-f4fa96826096","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ling, Z-H, Richmond, K, Yamagishi, J & Wang, R-H 2009, 'Integrating Articulatory Features Into HMM-Based Parametric Speech Synthesis', IEEE Transactions on Audio, Speech and Language Processing, vol. 17, no. 6, pp. 1171-1851. https://doi.org/10.1109/TASL.2009.2014796","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1590366332","display_name":null,"funder_award_id":"EP/E027741/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G1934935867","display_name":null,"funder_award_id":"Engineering and Physical Sciences R","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8452545418","display_name":null,"funder_award_id":"unknown","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8930459011","display_name":null,"funder_award_id":"EC FP7","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W51508392","https://openalex.org/W80543058","https://openalex.org/W144652315","https://openalex.org/W157899740","https://openalex.org/W177229737","https://openalex.org/W181114153","https://openalex.org/W1529897604","https://openalex.org/W1564657563","https://openalex.org/W1591172823","https://openalex.org/W1600722501","https://openalex.org/W1878590289","https://openalex.org/W1963627370","https://openalex.org/W1982854652","https://openalex.org/W1984905644","https://openalex.org/W1988550205","https://openalex.org/W2013317861","https://openalex.org/W2034829178","https://openalex.org/W2039800941","https://openalex.org/W2042691334","https://openalex.org/W2044010669","https://openalex.org/W2049633694","https://openalex.org/W2049686551","https://openalex.org/W2052382192","https://openalex.org/W2054764113","https://openalex.org/W2079869087","https://openalex.org/W2085013480","https://openalex.org/W2086699924","https://openalex.org/W2087110403","https://openalex.org/W2091650508","https://openalex.org/W2108674328","https://openalex.org/W2111194146","https://openalex.org/W2132885390","https://openalex.org/W2153914468","https://openalex.org/W2154920538","https://openalex.org/W2155077107","https://openalex.org/W2160006372","https://openalex.org/W2166823384","https://openalex.org/W2204452154","https://openalex.org/W2400063444","https://openalex.org/W3129711340","https://openalex.org/W4301420498","https://openalex.org/W6603264027","https://openalex.org/W6606471501","https://openalex.org/W6635376843","https://openalex.org/W6639371816","https://openalex.org/W6676044216","https://openalex.org/W6676358011","https://openalex.org/W6712610176"],"related_works":["https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W2108985546","https://openalex.org/W2038801705","https://openalex.org/W2433276473","https://openalex.org/W2077992636","https://openalex.org/W1537411440","https://openalex.org/W2535215250","https://openalex.org/W2049083033","https://openalex.org/W290673751"],"abstract_inverted_index":{"This":[0,38],"paper":[1],"presents":[2],"an":[3,73],"investigation":[4],"into":[5,11],"ways":[6],"of":[7,31,72,100,116,123,168,182,185],"integrating":[8],"articulatory":[9,34,79,142,178],"features":[10,35,80,179],"hidden":[12],"Markov":[13],"model":[14,85,134],"(HMM)-based":[15],"parametric":[16],"speech":[17,125,161,170],"synthesis.":[18],"In":[19],"broad":[20,60],"terms,":[21],"this":[22,59],"may":[23,39],"be":[24,42,127,172],"achieved":[25],"by":[26,175],"estimating":[27],"the":[28,70,97,114,121,152,183],"joint":[29],"distribution":[30],"acoustic":[32,52,83,102,117,140,187],"and":[33,89,120,132,141],"during":[36],"training.":[37],"in":[40,44,69],"turn":[41],"used":[43],"conjunction":[45],"with":[46],"a":[47],"maximum-likelihood":[48],"criterion":[49],"to":[50,81],"produce":[51],"synthesis":[53,75,162,188],"parameters":[54,103],"for":[55,138],"generating":[56],"speech.":[57],"Within":[58],"approach,":[61],"we":[62],"explore":[63],"several":[64],"variations":[65],"that":[66,113,150],"are":[67,136],"possible":[68],"construction":[71],"HMM-based":[74],"system":[76],"which":[77],"allow":[78],"influence":[82],"modeling:":[84],"clustering,":[86],"state":[87],"synchrony":[88],"cross-stream":[90],"feature":[91,157],"dependency.":[92],"Performance":[93],"is":[94],"evaluated":[95],"using":[96],"RMS":[98],"error":[99],"generated":[101,177],"as":[104,106,180],"well":[105],"formal":[107],"listening":[108],"tests.":[109],"Our":[110],"results":[111],"show":[112],"accuracy":[115],"parameter":[118],"prediction":[119],"naturalness":[122],"synthesized":[124],"can":[126,159,171],"improved":[128],"when":[129],"shared":[130],"clustering":[131],"asynchronous-state":[133],"structures":[135],"adopted":[137],"combined":[139],"features.":[143],"Most":[144],"significantly,":[145],"however,":[146],"our":[147],"experiments":[148],"demonstrate":[149],"modeling":[151],"dependency":[153],"between":[154],"these":[155],"two":[156],"streams":[158],"make":[160],"systems":[163],"more":[164],"flexible.":[165],"The":[166],"characteristics":[167],"synthetic":[169],"easily":[173],"controlled":[174],"modifying":[176],"part":[181],"process":[184],"producing":[186],"parameters.":[189]},"counts_by_year":[{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":14},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":8}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}