{"id":"https://openalex.org/W2019395288","doi":"https://doi.org/10.1109/icassp.2010.5495559","title":"A comparison of supervised and unsupervised cross-lingual speaker adaptation approaches for HMM-based speech synthesis","display_name":"A comparison of supervised and unsupervised cross-lingual speaker adaptation approaches for HMM-based speech synthesis","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2019395288","doi":"https://doi.org/10.1109/icassp.2010.5495559","mag":"2019395288"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495559","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/146444","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068810492","display_name":"Hui Liang","orcid":"https://orcid.org/0000-0001-6632-0929"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Hui Liang","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland","\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105301736","display_name":"John Dines","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"John Dines","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017257483","display_name":"Lakshmi Babu Saheer","orcid":"https://orcid.org/0000-0002-5263-596X"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]},{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Lakshmi Saheer","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland","\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068810492"],"corresponding_institution_ids":["https://openalex.org/I5124864","https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":8.3787,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.97450854,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4598","last_page":"4601"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9930999875068665,"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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9907000064849854,"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":0.847066342830658},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7402422428131104},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7206525206565857},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7125954031944275},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5641634464263916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5522904396057129},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4630665183067322},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4559427499771118},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.43915557861328125},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.42242830991744995},{"id":"https://openalex.org/keywords/optimal-distinctiveness-theory","display_name":"Optimal distinctiveness theory","score":0.418100506067276},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4108472466468811},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07340708374977112}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.847066342830658},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7402422428131104},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7206525206565857},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7125954031944275},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5641634464263916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5522904396057129},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4630665183067322},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4559427499771118},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.43915557861328125},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.42242830991744995},{"id":"https://openalex.org/C47385372","wikidata":"https://www.wikidata.org/wiki/Q7098943","display_name":"Optimal distinctiveness theory","level":2,"score":0.418100506067276},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4108472466468811},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07340708374977112},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp.2010.5495559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495559","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:CiteSeerX.psu:10.1.1.176.1132","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.176.1132","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://publications.idiap.ch/downloads/papers/2009/Liang_ICASSP_2010.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:146444","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146444","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.epfl.ch:146445","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146445","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.tind.io:146444","is_oa":true,"landing_page_url":"http://publications.idiap.ch/index.php/publications/showcite/Liang_ICASSP_2010","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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":"report"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:146444","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146444","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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":"","raw_type":"Text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.47999998927116394},{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W113498433","https://openalex.org/W1518816749","https://openalex.org/W1553129813","https://openalex.org/W1600722501","https://openalex.org/W2114010348","https://openalex.org/W2153914468","https://openalex.org/W2154920538","https://openalex.org/W4301420498"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2099333848"],"abstract_inverted_index":{"The":[0,87],"EMIME":[1,132],"project":[2],"aims":[3],"to":[4,22,46,81,119],"build":[5],"a":[6,15,140],"personalized":[7],"speech-to-speech":[8],"translator,":[9],"such":[10],"that":[11,26,120],"spoken":[12,24],"input":[13],"of":[14,64,89,112,121,127],"user":[16],"in":[17,34,125,130],"one":[18,44],"language":[19],"is":[20,100,117],"used":[21],"produce":[23],"output":[25],"still":[27],"sounds":[28],"like":[29],"the":[30,47,78,110,122,131],"user's":[31],"voice":[32],"however":[33],"another":[35],"language.":[36],"This":[37],"distinctiveness":[38],"makes":[39],"unsupervised":[40,57,83,113],"cross-lingual":[41,59,84,114],"speaker":[42,85,91,115],"adaptation":[43,92,116,129],"key":[45],"project's":[48],"success.":[49],"So":[50],"far,":[51],"research":[52],"has":[53],"been":[54],"conducted":[55],"into":[56],"and":[58,68,104],"cases":[60],"separately":[61],"by":[62],"means":[63],"decision":[65],"tree":[66],"marginalization":[67],"HMM":[69],"state":[70],"mapping":[71],"respectively.":[72],"In":[73],"this":[74],"paper":[75],"we":[76],"combine":[77],"two":[79],"techniques":[80],"perform":[82],"adaptation.":[86],"performance":[88,111],"eight":[90],"systems":[93],"(supervised":[94],"vs.":[95,98],"unsupervised,":[96],"intra-lingual":[97],"cross-lingual)":[99],"compared":[101],"using":[102],"objective":[103],"subjective":[105],"evaluations.":[106],"Experimental":[107],"results":[108],"show":[109],"comparable":[118],"supervised":[123],"case":[124],"terms":[126],"spectrum":[128],"scenario,":[133],"even":[134],"though":[135],"automatically":[136],"obtained":[137],"transcriptions":[138],"have":[139],"very":[141],"high":[142],"phoneme":[143],"error":[144],"rate.":[145]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
