{"id":"https://openalex.org/W2140179613","doi":"https://doi.org/10.1109/icassp.2009.4960449","title":"Recent improvements of Probability Based Prosody Models for Unit Selection in concatenative Text-to-Speech","display_name":"Recent improvements of Probability Based Prosody Models for Unit Selection in concatenative Text-to-Speech","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2140179613","doi":"https://doi.org/10.1109/icassp.2009.4960449","mag":"2140179613"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960449","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960449","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":"conference-paper","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/A5101555889","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0002-0678-0154"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102952206","display_name":"Liang Gu","orcid":"https://orcid.org/0000-0002-9719-7510"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liang Gu","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074146436","display_name":"Yuqing Gao","orcid":"https://orcid.org/0000-0001-8709-8378"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuqing Gao","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3777","last_page":"3780"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9980999827384949,"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/T12031","display_name":"Speech and dialogue systems","score":0.9962999820709229,"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":0.8628796339035034},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7062104344367981},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6549397706985474},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.6311659216880798},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6253878474235535},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5466112494468689},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5050330758094788},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4881366193294525},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4157904386520386},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3733257055282593},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.17034712433815002},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14131972193717957}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8628796339035034},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7062104344367981},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6549397706985474},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.6311659216880798},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6253878474235535},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5466112494468689},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5050330758094788},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4881366193294525},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4157904386520386},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3733257055282593},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.17034712433815002},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14131972193717957},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2009.4960449","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960449","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W16930393","https://openalex.org/W39235475","https://openalex.org/W42451021","https://openalex.org/W75668230","https://openalex.org/W191556021","https://openalex.org/W214260445","https://openalex.org/W1577446345","https://openalex.org/W2049510512","https://openalex.org/W2137851479","https://openalex.org/W2398649184","https://openalex.org/W6712526093"],"related_works":["https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W3149582125","https://openalex.org/W1984347656","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W152045069","https://openalex.org/W652196294","https://openalex.org/W2368700418"],"abstract_inverted_index":{"The":[0],"work":[1],"presented":[2],"in":[3,21,41],"this":[4],"paper":[5,10],"is":[6,36],"subsequent":[7],"to":[8],"the":[9,24,42,47],"ldquoProbability":[11],"Based":[12],"Prosody":[13],"Model":[14],"for":[15,29],"Unit":[16],"Selectionrdquo":[17],"which":[18,45],"was":[19],"published":[20],"ICASSP'2004.":[22],"In":[23],"improved":[25],"probability":[26,40,59],"prosody":[27],"model":[28],"corpus":[30],"based":[31],"concatenative":[32],"Text-to-Speech":[33],"(TTS),":[34],"likelihood":[35,64],"replaced":[37],"with":[38],"posterior":[39,58],"cost":[43],"functions":[44],"conduct":[46],"following":[48],"step,":[49],"unit":[50],"selection.":[51],"Objective":[52],"and":[53,68],"subjective":[54],"experiments":[55],"show":[56],"that":[57],"has":[60],"obvious":[61],"advantages":[62],"over":[63],"on":[65],"robustness,":[66],"flexibility":[67],"overall":[69],"quality.":[70]},"counts_by_year":[{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}