{"id":"https://openalex.org/W2147868561","doi":"https://doi.org/10.1109/icassp.2009.4960450","title":"Improved prosody generation by maximizing joint likelihood of state and longer units","display_name":"Improved prosody generation by maximizing joint likelihood of state and longer units","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2147868561","doi":"https://doi.org/10.1109/icassp.2009.4960450","mag":"2147868561"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960450","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960450","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/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":true,"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/A5102765381","display_name":"Zhizheng Wu","orcid":"https://orcid.org/0009-0001-1192-9857"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]},{"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":"Zhizheng Wu","raw_affiliation_strings":["College of Software, Nankai University, China","Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"College of Software, Nankai University, China","institution_ids":["https://openalex.org/I205237279"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","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 K. Soong","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100342006"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":4.798,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.95160218,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"20","issue":null,"first_page":"3781","last_page":"3784"},"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":0.9973999857902527,"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":0.9961000084877014,"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/prosody","display_name":"Prosody","score":0.9492663741111755},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.786986768245697},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7379218339920044},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7189473509788513},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6688082218170166},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6310961842536926},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6000425815582275},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5875772833824158},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5649614930152893},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4550611972808838},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43856632709503174},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3965669572353363},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20495477318763733},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1580120325088501},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12409394979476929},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09508723020553589}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.9492663741111755},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.786986768245697},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7379218339920044},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7189473509788513},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6688082218170166},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6310961842536926},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6000425815582275},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5875772833824158},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5649614930152893},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4550611972808838},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43856632709503174},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3965669572353363},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20495477318763733},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1580120325088501},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12409394979476929},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09508723020553589},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2009.4960450","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960450","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":26,"referenced_works":["https://openalex.org/W113106864","https://openalex.org/W133559434","https://openalex.org/W199136187","https://openalex.org/W338723207","https://openalex.org/W1480376833","https://openalex.org/W1512429158","https://openalex.org/W1514737389","https://openalex.org/W1554944419","https://openalex.org/W1979449467","https://openalex.org/W1982794085","https://openalex.org/W1993523973","https://openalex.org/W2000513720","https://openalex.org/W2010745337","https://openalex.org/W2106421426","https://openalex.org/W2107060717","https://openalex.org/W2154920538","https://openalex.org/W2376932199","https://openalex.org/W2915907762","https://openalex.org/W6604530167","https://openalex.org/W6605419763","https://openalex.org/W6608170980","https://openalex.org/W6611500205","https://openalex.org/W6630838124","https://openalex.org/W6676002441","https://openalex.org/W6759540021","https://openalex.org/W7056901721"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W2393726922","https://openalex.org/W2366752344"],"abstract_inverted_index":{"The":[0,31,78,121],"current":[1],"state-of-art":[2],"HMM-bsed":[3],"TTS":[4],"can":[5],"produce":[6],"highly":[7],"intelligible":[8],"output":[9],"speech":[10],"and":[11,111,127],"deliver":[12],"a":[13,43,51,57],"decent":[14],"segmental":[15],"quality.":[16],"However,":[17],"its":[18],"prosody,":[19],"especially":[20],"at":[21,56],"the":[22,40,65,85,96,117],"phrase":[23,60],"or":[24,59],"sentence":[25,58],"level,":[26],"tends":[27],"to":[28,39,89,103],"be":[29],"bland.":[30],"blandness":[32],"of":[33,67,99],"synthesized":[34],"prosody":[35,66,93],"is":[36,46],"partially":[37],"due":[38],"fact":[41],"that":[42],"state-based":[44,118],"HMM":[45],"rather":[47],"inadequate":[48],"in":[49,108],"modeling":[50],"global,":[52],"hierarchical":[53],"prosodic":[54],"structure":[55],"level.":[61],"In":[62],"this":[63],"study,":[64],"longer":[68],"units":[69],"are":[70,81,123],"first":[71],"modeled":[72],"explicitly":[73],"by":[74,94],"appropriate":[75],"parametric":[76],"distributions.":[77],"resultant":[79],"models":[80,88],"then":[82],"integrated":[83],"with":[84],"state-level":[86],"baseline":[87,119],"generate":[90],"an":[91],"optimal":[92],"maximizing":[95],"joint":[97],"likelihood":[98],"all,":[100],"from":[101],"state":[102],"longer,":[104],"units.":[105],"Experimental":[106],"results":[107],"both":[109,124],"Mandarin":[110],"English":[112],"show":[113],"consistent":[114],"improvements":[115,122],"over":[116],"system.":[120],"objectively":[125],"measurable":[126],"subjectively":[128],"perceivable.":[129]},"counts_by_year":[{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}