{"id":"https://openalex.org/W2152834109","doi":"https://doi.org/10.1109/icassp.2006.1660081","title":"Prosody Generation for Speech-to-Speech Translation","display_name":"Prosody Generation for Speech-to-Speech Translation","publication_year":2006,"publication_date":"2006-08-03","ids":{"openalex":"https://openalex.org/W2152834109","doi":"https://doi.org/10.1109/icassp.2006.1660081","mag":"2152834109"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2006.1660081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","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/A5051689632","display_name":"Pablo Daniel Ag\u00fcero","orcid":null},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"P.D. Aguero","raw_affiliation_strings":["TALP Research Center, Universitat Polilt\u00e8cnica de Catalunya, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TALP Research Center, Universitat Polilt\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008355354","display_name":"Jordi Adell Segura","orcid":"https://orcid.org/0000-0003-4369-6485"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"J. Adell","raw_affiliation_strings":["TALP Research Center, Universitat Polilt\u00e8cnica de Catalunya, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TALP Research Center, Universitat Polilt\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000405202","display_name":"Antonio Bonafonte","orcid":"https://orcid.org/0000-0002-6240-9915"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"A. Bonafonte","raw_affiliation_strings":["TALP Research Center, Universitat Polilt\u00e8cnica de Catalunya, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TALP Research Center, Universitat Polilt\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9617848"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"557"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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":0.9984999895095825,"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":0.848236083984375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7971086502075195},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.7458540201187134},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6549309492111206},{"id":"https://openalex.org/keywords/intonation","display_name":"Intonation (linguistics)","score":0.6489524841308594},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.625856876373291},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6201856732368469},{"id":"https://openalex.org/keywords/chinese-speech-synthesis","display_name":"Chinese speech synthesis","score":0.6004407405853271},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5996444821357727},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5792746543884277},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4813850224018097},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4251707196235657},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.32304590940475464},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.27100688219070435}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.848236083984375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7971086502075195},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.7458540201187134},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6549309492111206},{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.6489524841308594},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.625856876373291},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6201856732368469},{"id":"https://openalex.org/C73411735","wikidata":"https://www.wikidata.org/wiki/Q16369","display_name":"Chinese speech synthesis","level":4,"score":0.6004407405853271},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5996444821357727},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5792746543884277},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4813850224018097},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4251707196235657},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.32304590940475464},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.27100688219070435},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2006.1660081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.75.2159","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.75.2159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://gps-tsc.upc.es/veu/research/pubs/download/PDA_Pro_06.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.79.6949","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.79.6949","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://gps-tsc.upc.es/veu/personal/jadell/pdfs/agueroICASSP06.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.75,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W283543405","https://openalex.org/W1567168389","https://openalex.org/W1905911528","https://openalex.org/W1973923101","https://openalex.org/W2397129245","https://openalex.org/W2407870089","https://openalex.org/W6610260454","https://openalex.org/W6712351000"],"related_works":["https://openalex.org/W2349468610","https://openalex.org/W2338806053","https://openalex.org/W2772686614","https://openalex.org/W4200068392","https://openalex.org/W2152834109","https://openalex.org/W231741463","https://openalex.org/W301864623","https://openalex.org/W4379540238","https://openalex.org/W2537969829","https://openalex.org/W2559880587"],"abstract_inverted_index":{"This":[0],"paper":[1],"deals":[2],"with":[3],"speech":[4,49,72,94,101],"synthesis":[5],"in":[6,32,69,76,91,98,105,116],"the":[7,39,47,64,70,77,99,106,117],"framework":[8,38],"of":[9,53,66],"speech-to-speech":[10],"translation.":[11],"Our":[12],"current":[13],"focus":[14],"is":[15,41],"to":[16,30,73,122],"translate":[17],"speeches":[18],"or":[19],"conversations":[20],"between":[21],"humans":[22],"so":[23],"that":[24,89],"a":[25,51,92,113],"third":[26],"person":[27],"can":[28],"listen":[29],"them":[31],"its":[33],"own":[34],"language.":[35,79],"In":[36,59],"this":[37,60],"style":[40],"not":[42],"written":[43],"but":[44],"spoken":[45],"and":[46],"original":[48,71],"includes":[50],"lot":[52],"non-linguistic":[54],"information":[55],"(as":[56],"speaker":[57],"emotion).":[58],"work":[61],"we":[62],"propose":[63],"use":[65],"prosodic":[67],"features":[68,81],"produce":[74],"prosody":[75],"target":[78,107],"Relevant":[80],"are":[82,103],"found":[83],"using":[84],"an":[85],"unsupervised":[86],"clustering":[87],"algorithm":[88],"finds,":[90],"bilingual":[93],"corpus,":[95],"intonation":[96],"clusters":[97],"source":[100],"which":[102],"relevant":[104],"speech.":[108],"Preliminary":[109],"results":[110],"already":[111],"show":[112],"significant":[114],"improvement":[115],"synthetic":[118],"quality":[119],"(from":[120],"MOS=3.40":[121],"MOS=3.65)":[123]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
