{"id":"https://openalex.org/W1660564604","doi":"https://doi.org/10.21437/interspeech.2010-238","title":"An analysis of language mismatch in HMM state mapping-based cross-lingual speaker adaptation","display_name":"An analysis of language mismatch in HMM state mapping-based cross-lingual speaker adaptation","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W1660564604","doi":"https://doi.org/10.21437/interspeech.2010-238","mag":"1660564604"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-238","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-238","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://publications.idiap.ch/downloads/papers/2010/Liang_INTERSPEECH_2010.pdf","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/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"],"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","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"],"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5068810492"],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":3.716,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.92906035,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"622","last_page":"625"},"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":0.9958999752998352,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9926999807357788,"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":0.8189887404441833},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.77078777551651},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7055485248565674},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6069467067718506},{"id":"https://openalex.org/keywords/first-language","display_name":"First language","score":0.46894571185112},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41905373334884644},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.41566723585128784},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4120723605155945},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.38659292459487915},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17133235931396484},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07054716348648071}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8189887404441833},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.77078777551651},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7055485248565674},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6069467067718506},{"id":"https://openalex.org/C171041071","wikidata":"https://www.wikidata.org/wiki/Q36870","display_name":"First language","level":2,"score":0.46894571185112},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41905373334884644},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.41566723585128784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4120723605155945},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.38659292459487915},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17133235931396484},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07054716348648071},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"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":5,"locations":[{"id":"doi:10.21437/interspeech.2010-238","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-238","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.tind.io:150600","is_oa":true,"landing_page_url":"http://publications.idiap.ch/index.php/publications/showcite/Liang_Idiap-RR-16-2010","pdf_url":"http://publications.idiap.ch/downloads/papers/2010/Liang_INTERSPEECH_2010.pdf","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":"conference proceedings"},{"id":"pmh:oai:infoscience.tind.io:150628","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/150628","pdf_url":"http://publications.idiap.ch/downloads/reports/2010/Liang_Idiap-RR-16-2010.pdf","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/150628","raw_type":"Text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.371.244","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.371.244","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/2010/Liang_INTERSPEECH_2010.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:150600","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/150600","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"}],"best_oa_location":{"id":"pmh:oai:infoscience.tind.io:150600","is_oa":true,"landing_page_url":"http://publications.idiap.ch/index.php/publications/showcite/Liang_Idiap-RR-16-2010","pdf_url":"http://publications.idiap.ch/downloads/papers/2010/Liang_INTERSPEECH_2010.pdf","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":"conference proceedings"},"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W1660564604.pdf"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W113498433","https://openalex.org/W1518816749","https://openalex.org/W2002342963","https://openalex.org/W2019395288","https://openalex.org/W2100340603","https://openalex.org/W2117418893","https://openalex.org/W2153914468"],"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/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"This":[0],"paper":[1],"provides":[2],"an":[3],"in-depth":[4],"analysis":[5,78],"of":[6,9,15,24,40],"the":[7,13,22,38],"impacts":[8],"language":[10,25,59,86,105],"mismatch":[11,26,43,60,106],"on":[12],"performance":[14],"cross-lingual":[16,52,92,99],"speaker":[17,53,80,100],"adaptation.":[18,54],"Our":[19,77],"work":[20],"confirms":[21],"influence":[23],"between":[27],"average":[28],"voice":[29],"distributions":[30],"for":[31,34,51],"synthesis":[32],"and":[33,37],"transform":[35],"estimation":[36],"necessity":[39],"eliminating":[41],"this":[42],"in":[44,88],"order":[45,89],"to":[46,74,90],"effectively":[47],"utilize":[48],"multiple":[49,67],"transforms":[50,72],"Specifically,":[55],"we":[56],"show":[57],"that":[58],"introduces":[61],"unwanted":[62],"language-specific":[63],"information":[64],"when":[65],"estimating":[66],"transforms,":[68],"thus":[69],"making":[70],"these":[71],"detrimental":[73],"adaptation":[75,93],"performance.":[76,94],"demonstrates":[79],"characteristics":[81,87],"should":[82],"be":[83],"separated":[84],"from":[85],"improve":[91],"Index":[95],"Terms:":[96],"HMM-based":[97],"TTS,":[98],"adaptation,":[101],"HMM":[102],"state":[103],"mapping,":[104]},"counts_by_year":[{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
