{"id":"https://openalex.org/W2137851479","doi":"https://doi.org/10.1109/icassp.2004.1326069","title":"Probability based prosody model for unit selection","display_name":"Probability based prosody model for unit selection","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2137851479","doi":"https://doi.org/10.1109/icassp.2004.1326069","mag":"2137851479"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 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/A5007142915","display_name":"MA Xi-jun","orcid":null},"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/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Xijun Ma","raw_affiliation_strings":["IBM China Research Laboratory, China","IBM, China Research Lab., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM China Research Laboratory, China","institution_ids":["https://openalex.org/I4210126794"]},{"raw_affiliation_string":"IBM, China Research Lab., China","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100756628","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0001-5556-3896"},"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/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["IBM China Research Laboratory, China","IBM, China Research Lab., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM China Research Laboratory, China","institution_ids":["https://openalex.org/I4210126794"]},{"raw_affiliation_string":"IBM, China Research Lab., China","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102492475","display_name":"Weibin Zhu","orcid":null},"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/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Weibin Zhu","raw_affiliation_strings":["IBM China Research Laboratory, China","IBM, China Research Lab., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM China Research Laboratory, China","institution_ids":["https://openalex.org/I4210126794"]},{"raw_affiliation_string":"IBM, China Research Lab., China","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100736302","display_name":"Qin Shi","orcid":"https://orcid.org/0000-0002-9608-0345"},"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/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Qin Shi","raw_affiliation_strings":["IBM China Research Laboratory, China","IBM, China Research Lab., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM China Research Laboratory, China","institution_ids":["https://openalex.org/I4210126794"]},{"raw_affiliation_string":"IBM, China Research Lab., China","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109995018","display_name":"Ling Jin","orcid":"https://orcid.org/0000-0002-7364-913X"},"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/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Ling Jin","raw_affiliation_strings":["IBM China Research Laboratory, China","IBM, China Research Lab., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM China Research Laboratory, China","institution_ids":["https://openalex.org/I4210126794"]},{"raw_affiliation_string":"IBM, China Research Lab., China","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.313,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.89937826,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"649"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9987999796867371,"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":0.9948999881744385,"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":0.89304518699646},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6576110124588013},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6488378047943115},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5990374088287354},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5022192001342773},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45517662167549133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43993180990219116},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.43619465827941895},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.43272650241851807},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.4246060848236084},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.41883155703544617},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2390921413898468},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.16516542434692383},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07240849733352661}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.89304518699646},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6576110124588013},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6488378047943115},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5990374088287354},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5022192001342773},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45517662167549133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43993180990219116},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.43619465827941895},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.43272650241851807},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.4246060848236084},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.41883155703544617},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2390921413898468},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16516542434692383},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07240849733352661},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2004.1326069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 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":16,"referenced_works":["https://openalex.org/W162654330","https://openalex.org/W191556021","https://openalex.org/W1553896573","https://openalex.org/W1594337151","https://openalex.org/W1704572586","https://openalex.org/W2049510512","https://openalex.org/W2096466030","https://openalex.org/W2102129020","https://openalex.org/W2128221272","https://openalex.org/W2315348142","https://openalex.org/W2543721542","https://openalex.org/W6606697926","https://openalex.org/W6607864401","https://openalex.org/W6633004830","https://openalex.org/W6635375606","https://openalex.org/W6679317373"],"related_works":["https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W3149582125","https://openalex.org/W1984347656","https://openalex.org/W1965141925","https://openalex.org/W2465421051","https://openalex.org/W652196294","https://openalex.org/W2368700418","https://openalex.org/W2587342322","https://openalex.org/W2540115864"],"abstract_inverted_index":{"Most":[0],"modern":[1],"text-to-speech":[2],"(TTS)":[3],"systems":[4,91],"are":[5,29,102],"unit":[6,34,70,87],"selection":[7,88],"style.":[8],"In":[9],"this":[10],"kind":[11],"of":[12,47,100],"system,":[13],"the":[14,45,65,72,79,95,105],"predicted":[15],"prosody":[16,41,48],"values,":[17],"such":[18],"as":[19],"pitch,":[20],"duration":[21],"and":[22,64,71,97],"energy":[23],"values":[24,49],"for":[25,86],"each":[26],"synthesis":[27],"unit,":[28],"important":[30],"factors":[31],"to":[32],"conduct":[33],"selection.":[35],"We":[36],"present":[37],"a":[38,51,59,68,98],"probability":[39,81],"based":[40],"model":[42,62],"in":[43,50],"which":[44],"distribution":[46],"given":[52],"context":[53,73],"equivalent":[54,74],"cluster":[55,75],"is":[56,76,92],"described":[57],"by":[58,78],"Gaussian":[60],"mixture":[61],"(GMM),":[63],"distance":[66],"between":[67],"candidate":[69],"defined":[77],"GMM":[80],"output.":[82],"A":[83],"novel":[84],"framework":[85],"style":[89],"TTS":[90],"derived":[93],"from":[94],"model,":[96],"series":[99],"experiments":[101],"done":[103],"on":[104],"framework.":[106]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}