{"id":"https://openalex.org/W2085245374","doi":"https://doi.org/10.1109/icassp.2010.5495561","title":"Improved modeling for F0 generation and V/U decision in HMM-based TTS","display_name":"Improved modeling for F0 generation and V/U decision in HMM-based TTS","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2085245374","doi":"https://doi.org/10.1109/icassp.2010.5495561","mag":"2085245374"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495561","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495561","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 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/A5100375544","display_name":"Qingqing Zhang","orcid":"https://orcid.org/0000-0002-5507-466X"},"institutions":[{"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"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qingqing Zhang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","ThinkIT Speech Laboratory, Institute of Acoustics, Chinese Academy and Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"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/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Frank Soong","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342006","display_name":"Yao Qian","orcid":"https://orcid.org/0000-0003-1855-9630"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Qian","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061850214","display_name":"Zhijie Yan","orcid":"https://orcid.org/0000-0001-8065-0748"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijie Yan","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111847664","display_name":"Jielin Pan","orcid":null},"institutions":[{"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":false,"raw_author_name":"Jielin Pan","raw_affiliation_strings":["ThinkIT Speech Laboratory, Institute of Acoustics, Chinese Academy and Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"ThinkIT Speech Laboratory, Institute of Acoustics, Chinese Academy and Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100425112","display_name":"Yonghong Yan","orcid":"https://orcid.org/0000-0001-6907-5770"},"institutions":[{"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":false,"raw_author_name":"Yonghong Yan","raw_affiliation_strings":["ThinkIT Speech Laboratory, Institute of Acoustics, Chinese Academy and Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"ThinkIT Speech Laboratory, Institute of Acoustics, Chinese Academy and Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100375544"],"corresponding_institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":5.4125,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.95563776,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4606","last_page":"4609"},"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":0.9994999766349792,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8472447395324707},{"id":"https://openalex.org/keywords/voice","display_name":"Voice","score":0.6702947020530701},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6464061737060547},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6444864869117737},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5667293667793274},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5654803514480591},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.5034617781639099},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4889785051345825},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4645533263683319},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4612734317779541},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4398180842399597},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4250485897064209},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4017244875431061}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8472447395324707},{"id":"https://openalex.org/C552089266","wikidata":"https://www.wikidata.org/wiki/Q494510","display_name":"Voice","level":2,"score":0.6702947020530701},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6464061737060547},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6444864869117737},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5667293667793274},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5654803514480591},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.5034617781639099},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4889785051345825},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4645533263683319},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4612734317779541},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4398180842399597},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4250485897064209},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4017244875431061},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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.2010.5495561","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495561","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7799999713897705,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W50577135","https://openalex.org/W72216074","https://openalex.org/W205514123","https://openalex.org/W1559184314","https://openalex.org/W1592103878","https://openalex.org/W1963627370","https://openalex.org/W1979449467","https://openalex.org/W1993523973","https://openalex.org/W2039995614","https://openalex.org/W2049686551","https://openalex.org/W2103279870","https://openalex.org/W2141684970","https://openalex.org/W2154920538","https://openalex.org/W4402490932","https://openalex.org/W6633512198","https://openalex.org/W6660469439"],"related_works":["https://openalex.org/W2036753972","https://openalex.org/W1996861825","https://openalex.org/W2079621619","https://openalex.org/W2046280377","https://openalex.org/W4388535697","https://openalex.org/W2497205885","https://openalex.org/W2036128733","https://openalex.org/W175280642","https://openalex.org/W2688184458","https://openalex.org/W2147186888"],"abstract_inverted_index":{"The":[0,162],"HMM-based":[1,111],"TTS":[2],"can":[3],"produce":[4],"a":[5,85,96,155],"highly":[6],"intelligible":[7],"and":[8,30,107,136,149,154,168],"decent":[9],"quality":[10],"voice.":[11],"However,":[12],"sometimes":[13],"the":[14,27,38,45,52,60,76,102,117,143],"synthesized":[15],"speech":[16],"exhibits":[17],"perceptibly":[18],"annoying":[19],"glitches":[20],"due":[21],"to":[22,74,99,146],"F0":[23,35,42,80,105,124,134,147],"extraction":[24,81],"errors":[25,33,82],"in":[26,34,83,123,133],"training":[28,84],"data":[29],"voiced/unvoiced":[31],"swapping":[32],"generation.":[36],"In":[37,91],"conventional":[39],"MSD":[40],"based":[41,71],"modeling":[43,101,135,148],"[10],":[44],"dual":[46],"but":[47],"incompatible":[48],"two":[49],"probabilistic":[50],"spaces,":[51],"continuous":[53,104],"probability":[54,62],"density":[55],"for":[56,63,89,110,137],"voiced":[57],"observations":[58],"or":[59],"discrete":[61],"unvoiced":[64],"observations,":[65],"prevent":[66],"us":[67],"from":[68],"using":[69],"likelihood":[70],"frame":[72],"occupancy":[73],"alleviate":[75],"deteriorating":[77],"effect":[78],"of":[79],"more":[86],"robust":[87],"model":[88],"synthesis.":[90],"this":[92],"paper,":[93],"we":[94],"propose":[95],"new":[97,144],"approach":[98,145],"improved":[100],"piece-wise":[103],"trajectory":[106],"v/u":[108,138],"decision":[109],"TTS.":[112],"Voicing":[113],"strength,":[114],"characterized":[115],"by":[116],"normalized":[118],"correlation":[119],"coefficient":[120],"magnitude":[121],"calculated":[122],"feature":[125,132],"extraction,":[126],"is":[127],"used":[128],"as":[129],"an":[130],"additional":[131],"decision.":[139],"Experimental":[140],"results":[141],"show":[142],"generation":[150],"outperforms":[151],"MSD-HMM":[152],"method":[153,159],"newly":[156],"proposed":[157],"GTD-HMM":[158],"[9]":[160],"significantly.":[161],"improvements":[163],"are":[164],"both":[165],"objectively":[166],"measurable":[167],"subjectively":[169],"perceivable.":[170]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}