{"id":"https://openalex.org/W2008805730","doi":"https://doi.org/10.1109/icassp.2010.5495558","title":"Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis","display_name":"Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2008805730","doi":"https://doi.org/10.1109/icassp.2010.5495558","mag":"2008805730"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495558","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://era.ed.ac.uk/bitstream/1842/4657/1/oura_icassp2010.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049909008","display_name":"Keiichiro Oura","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiichiro Oura","raw_affiliation_strings":["Department of Computer Science and Engineering, Nagoya Institute of Technology, Japan","[Department of Computer Science and Engineering, Nagoya Institute of Technology, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Nagoya Institute of Technology, Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"[Department of Computer Science and Engineering, Nagoya Institute of Technology, Japan]","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103023678","display_name":"Keiichi Tokuda","orcid":"https://orcid.org/0000-0001-6143-0133"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiichi Tokuda","raw_affiliation_strings":["Department of Computer Science and Engineering, Nagoya Institute of Technology, Japan","[Department of Computer Science and Engineering, Nagoya Institute of Technology, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Nagoya Institute of Technology, Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"[Department of Computer Science and Engineering, Nagoya Institute of Technology, Japan]","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, UK","The Centre for Speech Technology Research, University of Edinburgh, UK#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK#TAB#","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, UK","The Centre for Speech Technology Research, University of Edinburgh, UK#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK#TAB#","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060282305","display_name":"Mirjam Wester","orcid":"https://orcid.org/0000-0002-3199-0081"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mirjam Wester","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, UK","The Centre for Speech Technology Research, University of Edinburgh, UK#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK#TAB#","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4594","last_page":"4597"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9966999888420105,"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":0.9941999912261963,"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/computer-science","display_name":"Computer science","score":0.8370294570922852},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7723199129104614},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7177071571350098},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6358195543289185},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5956910252571106},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5042496919631958},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.49573051929473877},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.47759461402893066},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.46779757738113403},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46193185448646545},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44666796922683716},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.37985387444496155},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09552860260009766},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.06671956181526184},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06050926446914673}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8370294570922852},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7723199129104614},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7177071571350098},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6358195543289185},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5956910252571106},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5042496919631958},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.49573051929473877},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.47759461402893066},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.46779757738113403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46193185448646545},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44666796922683716},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.37985387444496155},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09552860260009766},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.06671956181526184},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06050926446914673},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2010.5495558","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:era.ed.ac.uk:1842/4657","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/4657","pdf_url":"https://era.ed.ac.uk/bitstream/1842/4657/1/oura_icassp2010.pdf","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.185.1769","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.185.1769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.ed.ac.uk/downloads/publications/2010/oura_icassp2010.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:era.ed.ac.uk:1842/4657","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/4657","pdf_url":"https://era.ed.ac.uk/bitstream/1842/4657/1/oura_icassp2010.pdf","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2008805730.pdf","grobid_xml":"https://content.openalex.org/works/W2008805730.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W113498433","https://openalex.org/W1573315856","https://openalex.org/W1580849279","https://openalex.org/W1593598571","https://openalex.org/W1600722501","https://openalex.org/W1920064753","https://openalex.org/W2002342963","https://openalex.org/W2019395288","https://openalex.org/W2100340603","https://openalex.org/W2108153551","https://openalex.org/W2113106066","https://openalex.org/W2114010348","https://openalex.org/W2117418893","https://openalex.org/W2124219499","https://openalex.org/W2142937603","https://openalex.org/W2153914468","https://openalex.org/W6604531305","https://openalex.org/W6634224463","https://openalex.org/W6634520857","https://openalex.org/W6635599595","https://openalex.org/W6640141655","https://openalex.org/W6678332854","https://openalex.org/W7075637324"],"related_works":["https://openalex.org/W1497807607","https://openalex.org/W2159208002","https://openalex.org/W2108439317","https://openalex.org/W2162248568","https://openalex.org/W2810678173","https://openalex.org/W2165357419","https://openalex.org/W2160379050","https://openalex.org/W2295490460","https://openalex.org/W2992420079","https://openalex.org/W2042600255"],"abstract_inverted_index":{"In":[0],"the":[1,38,91],"EMIME":[2],"project,":[3],"we":[4],"are":[5,104],"developing":[6],"a":[7,17,51,65],"mobile":[8],"device":[9],"that":[10,16,85,95],"performs":[11],"personalized":[12],"speech-to-speech":[13],"translation":[14],"such":[15],"user's":[18,39],"spoken":[19,28],"input":[20],"in":[21,30],"one":[22],"language":[23],"is":[24],"used":[25],"to":[26,35,90],"produce":[27],"output":[29],"another":[31],"language,":[32],"while":[33],"continuing":[34],"sound":[36,88],"like":[37],"voice.":[40],"We":[41],"integrate":[42],"two":[43],"techniques,":[44],"unsupervised":[45,70,100],"adaptation":[46,60,73,103],"for":[47,61],"HMM-based":[48,62],"TTS":[49],"using":[50],"word-based":[52],"large-vocabulary":[53],"continuous":[54],"speech":[55],"recognizer":[56],"and":[57,94,99],"cross-lingual":[58,71,101],"speaker":[59,72,93,102],"TTS,":[63],"into":[64],"single":[66],"architecture.":[67],"Thus,":[68],"an":[69],"system":[74],"can":[75],"be":[76],"developed.":[77],"Listening":[78],"tests":[79],"show":[80],"very":[81],"promising":[82],"results,":[83],"demonstrating":[84],"adapted":[86],"voices":[87],"similar":[89],"target":[92],"differences":[96],"between":[97],"supervised":[98],"small.":[105]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}