{"id":"https://openalex.org/W2158474786","doi":"https://doi.org/10.1109/iscslp.2010.5684494","title":"Modeling prosody patterns for Chinese expressive text-to-speech synthesis","display_name":"Modeling prosody patterns for Chinese expressive text-to-speech synthesis","publication_year":2010,"publication_date":"2010-11-01","ids":{"openalex":"https://openalex.org/W2158474786","doi":"https://doi.org/10.1109/iscslp.2010.5684494","mag":"2158474786"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2010.5684494","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language 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/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":true,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua-CUHK Joint Research Center of Media Sciences, Technologies and Systems, Graduate School, Shenzhen, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center of Media Sciences, Technologies and Systems, Graduate School, Shenzhen, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053661520","display_name":"Lianhong Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Lianhong Cai","raw_affiliation_strings":["Tsinghua-CUHK Joint Research Center of Media Sciences, Technologies and Systems, Graduate School, Shenzhen, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center of Media Sciences, Technologies and Systems, Graduate School, Shenzhen, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Helen M. Meng","raw_affiliation_strings":["Tsinghua-CUHK Joint Research Center of Media Sciences, Technologies and Systems, Graduate School, Shenzhen, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center of Media Sciences, Technologies and Systems, Graduate School, Shenzhen, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102869280"],"corresponding_institution_ids":["https://openalex.org/I889458895","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.14900419,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"148","last_page":"152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.9988999962806702,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9970999956130981,"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/prosody","display_name":"Prosody","score":0.8133571147918701},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6999114155769348},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6989593505859375},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.6812077760696411},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5953884720802307},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5262486338615417},{"id":"https://openalex.org/keywords/syllabic-verse","display_name":"Syllabic verse","score":0.513911247253418},{"id":"https://openalex.org/keywords/tone","display_name":"Tone (literature)","score":0.4784793555736542},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4610883593559265},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4414322078227997},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4111175537109375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37657949328422546},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.24639824032783508}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8133571147918701},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6999114155769348},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6989593505859375},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.6812077760696411},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5953884720802307},{"id":"https://openalex.org/C21036866","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5262486338615417},{"id":"https://openalex.org/C194051139","wikidata":"https://www.wikidata.org/wiki/Q2629608","display_name":"Syllabic verse","level":2,"score":0.513911247253418},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.4784793555736542},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4610883593559265},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4414322078227997},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4111175537109375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37657949328422546},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24639824032783508},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2010.5684494","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W119516633","https://openalex.org/W139405928","https://openalex.org/W168929619","https://openalex.org/W182260620","https://openalex.org/W1793953714","https://openalex.org/W2102267302","https://openalex.org/W2124388456","https://openalex.org/W2161736993","https://openalex.org/W2165894799","https://openalex.org/W2395578248","https://openalex.org/W4390911368","https://openalex.org/W4390911445","https://openalex.org/W6604796382","https://openalex.org/W6606861284","https://openalex.org/W6711777497"],"related_works":["https://openalex.org/W2254467971","https://openalex.org/W3122402893","https://openalex.org/W2035036138","https://openalex.org/W2396586136","https://openalex.org/W2364360542","https://openalex.org/W2385848593","https://openalex.org/W57477431","https://openalex.org/W2365880448","https://openalex.org/W206077614","https://openalex.org/W2012074517"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"an":[3],"approach":[4,138],"for":[5,14,96],"modeling":[6],"the":[7,11,22,25,47,55,62,68,80,89,110,136],"prosody":[8,111],"patterns":[9],"of":[10,61,98],"acoustic":[12],"features":[13],"Chinese":[15],"expressive":[16,118,145],"text-to-speech":[17],"(TTS)":[18],"synthesis.":[19],"Based":[20],"on":[21,33,76,122],"observation":[23],"that":[24,50,106,135],"speaker":[26],"usually":[27],"tends":[28],"to":[29,113,117],"put":[30],"more":[31],"emphasis":[32],"one":[34],"particular":[35],"syllable":[36,45,49,82],"within":[37],"a":[38,84,103],"multi-syllabic":[39],"prosodic":[40,85],"word,":[41],"we":[42],"identify":[43],"such":[44],"as":[46],"core":[48,81],"can":[51,139],"be":[52],"derived":[53],"from":[54],"semantic":[56],"stress":[57],"and":[58,101,127],"tone":[59],"information":[60],"text":[63],"prompt.":[64],"We":[65,87],"then":[66],"classify":[67],"syllables":[69],"in":[70,83,143],"speech":[71,94,116,125],"into":[72,108],"four":[73,99],"classes,":[74,100],"based":[75],"their":[77],"relations":[78],"with":[79],"word.":[86],"analyze":[88],"contrastive":[90],"(neutral":[91],"versus":[92],"expressive)":[93],"recordings":[95,126],"each":[97],"develop":[102],"perturbation":[104],"model":[105],"takes":[107],"account":[109],"pattern":[112],"transform":[114],"neutral":[115,124,128],"speech.":[119,146],"Perceptual":[120],"experiments":[121],"both":[123],"TTS":[129],"outputs":[130],"involving":[131],"13":[132],"subjects":[133],"indicate":[134],"proposed":[137],"significantly":[140],"enhance":[141],"expressivity":[142],"synthesizing":[144]},"counts_by_year":[{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}