{"id":"https://openalex.org/W113498433","doi":"https://doi.org/10.21437/interspeech.2009-192","title":"State mapping based method for cross-lingual speaker adaptation in HMM-based speech synthesis","display_name":"State mapping based method for cross-lingual speaker adaptation in HMM-based speech synthesis","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W113498433","doi":"https://doi.org/10.21437/interspeech.2009-192","mag":"113498433"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-192","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://nitech.repo.nii.ac.jp/records/3403","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039492028","display_name":"Yi-Jian Wu","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":"Yi-Jian Wu","raw_affiliation_strings":["Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023240652","display_name":"Yoshihiko Nankaku","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":"Yoshihiko Nankaku","raw_affiliation_strings":["Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103023678","display_name":"Keiichi Tokuda","orcid":"https://orcid.org/0000-0001-6143-0133"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiichi Tokuda","raw_affiliation_strings":["National Institute of Information and Communications Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":14.0422,"has_fulltext":false,"cited_by_count":76,"citation_normalized_percentile":{"value":0.98916211,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"528","last_page":"531"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.989300012588501,"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/T10860","display_name":"Speech and Audio Processing","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/speech-recognition","display_name":"Speech recognition","score":0.7772344350814819},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7699697017669678},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7510576844215393},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5968414545059204},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5274052023887634},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5021815299987793},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.45537269115448},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4257740378379822},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37249407172203064},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08205801248550415},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07402229309082031}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7772344350814819},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7699697017669678},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7510576844215393},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5968414545059204},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5274052023887634},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5021815299987793},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.45537269115448},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4257740378379822},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37249407172203064},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08205801248550415},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07402229309082031},{"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:10.21437/interspeech.2009-192","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.582.9784","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.582.9784","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.sp.nitech.ac.jp/~bonanza/Paper/EMIME/yjwu_interspeech2009_CLSA.pdf","raw_type":"text"},{"id":"pmh:oai:irdb.nii.ac.jp:01154:0001435270","is_oa":true,"landing_page_url":"https://nitech.repo.nii.ac.jp/records/3403","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"INTERSPEECH 2009 10th Annual Conference of the International Speech Communication Association","raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01154:0001435270","is_oa":true,"landing_page_url":"https://nitech.repo.nii.ac.jp/records/3403","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"INTERSPEECH 2009 10th Annual Conference of the International Speech Communication Association","raw_type":"conference paper"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W129217914","https://openalex.org/W1514737389","https://openalex.org/W1533098358","https://openalex.org/W1593598571","https://openalex.org/W1600722501","https://openalex.org/W1602430027","https://openalex.org/W1974100992","https://openalex.org/W2000513720","https://openalex.org/W2002342963","https://openalex.org/W2096980176","https://openalex.org/W2115052578","https://openalex.org/W2123140629","https://openalex.org/W2139751012","https://openalex.org/W2166823384","https://openalex.org/W2286208596","https://openalex.org/W3036802551"],"related_works":["https://openalex.org/W1497807607","https://openalex.org/W1509309911","https://openalex.org/W1521049138","https://openalex.org/W2140022733","https://openalex.org/W2041797852","https://openalex.org/W2160379050","https://openalex.org/W2295490460","https://openalex.org/W2992420079","https://openalex.org/W2042600255","https://openalex.org/W129217914"],"abstract_inverted_index":{"A":[0],"phone":[1,83],"mapping-based":[2],"method":[3,26,80],"had":[4],"been":[5],"introduced":[6],"for":[7,27,61],"cross-lingual":[8,28,62,107],"speaker":[9,29,63,95,108,115],"adaptation":[10],"in":[11,38],"HMM-based":[12],"speech":[13,104],"syn-thesis.":[14],"In":[15,87],"this":[16],"paper,":[17],"we":[18],"continue":[19],"to":[20,55],"propose":[21],"a":[22],"state":[23,33,77],"mapping":[24,34,59,67,70,78,84,91,100],"based":[25,79,85],"adaptation,":[30,64,116],"where":[31],"the":[32,57,73,76,82,89,98],"between":[35],"voice":[36],"models":[37],"source":[39],"and":[40,68,97],"target":[41],"lan-guages":[42],"is":[43],"established":[44,58],"under":[45],"minimum":[46,117],"Kullback-Leibler":[47],"diver-gence":[48],"(KLD)":[49],"criterion.":[50],"We":[51],"introduce":[52],"two":[53],"approaches":[54],"use":[56],"information":[60],"including":[65],"data":[66,90],"transform":[69,99],"ap-proaches.":[71],"From":[72],"experimental":[74],"results,":[75],"outperformed":[81],"method.":[86],"addition,":[88],"approach":[92,101],"achieved":[93,102],"better":[94,103],"similarity,":[96],"quality":[105],"after":[106],"adaptation.":[109],"Index":[110],"Terms:":[111],"Speech":[112],"synthesis,":[113],"HMM,":[114],"generation":[118],"error,":[119],"linear":[120],"regression":[121]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":11}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}