{"id":"https://openalex.org/W2115052578","doi":"https://doi.org/10.1109/icassp.2009.4960573","title":"State mapping for cross-language speaker adaptation in TTS","display_name":"State mapping for cross-language speaker adaptation in TTS","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2115052578","doi":"https://doi.org/10.1109/icassp.2009.4960573","mag":"2115052578"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960573","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960573","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"article","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/A5003997327","display_name":"Yi\u2010Ning Chen","orcid":"https://orcid.org/0000-0003-4821-8511"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yi-Ning Chen","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070522921","display_name":"Yang Jiao","orcid":"https://orcid.org/0009-0003-4283-0088"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]},{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Jiao","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China","Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342006","display_name":"Yao Qian","orcid":"https://orcid.org/0000-0003-1855-9630"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Qian","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Frank K. Soong","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5003997327"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":2.1809,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.89343684,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"41","issue":null,"first_page":"4273","last_page":"4276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9904999732971191,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9800999760627747,"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/computer-science","display_name":"Computer science","score":0.8031214475631714},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.6652905941009521},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6538863778114319},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6192108988761902},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5983060002326965},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5744464993476868},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5127699971199036},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5096848011016846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47065985202789307},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4636788070201874},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.46191927790641785},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.45796990394592285},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4544234573841095},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.2547721564769745},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16611719131469727},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10485082864761353},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06989535689353943},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.06965675950050354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8031214475631714},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.6652905941009521},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6538863778114319},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6192108988761902},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5983060002326965},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5744464993476868},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5127699971199036},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5096848011016846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47065985202789307},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4636788070201874},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.46191927790641785},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.45796990394592285},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4544234573841095},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2547721564769745},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16611719131469727},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10485082864761353},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06989535689353943},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.06965675950050354},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2009.4960573","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960573","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W129217914","https://openalex.org/W308614314","https://openalex.org/W1533098358","https://openalex.org/W1538607601","https://openalex.org/W1965555277","https://openalex.org/W1973766695","https://openalex.org/W1974100992","https://openalex.org/W1984905644","https://openalex.org/W2006681603","https://openalex.org/W2099531983","https://openalex.org/W2119711888","https://openalex.org/W2123140629","https://openalex.org/W2132534451","https://openalex.org/W2152321560","https://openalex.org/W2154920538","https://openalex.org/W2166752834","https://openalex.org/W2167127461","https://openalex.org/W2395432258","https://openalex.org/W2401033099","https://openalex.org/W2587033535","https://openalex.org/W4212984011","https://openalex.org/W4234562309","https://openalex.org/W4250410815","https://openalex.org/W6674798237","https://openalex.org/W6683933629"],"related_works":["https://openalex.org/W2364370872","https://openalex.org/W4389272081","https://openalex.org/W2053269318","https://openalex.org/W135211875","https://openalex.org/W2052269122","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W1591475660","https://openalex.org/W2359614599"],"abstract_inverted_index":{"Cross-language":[0],"speaker":[1,13],"adaptation":[2,127],"has":[3,48],"many":[4],"interesting":[5],"applications,":[6],"e.g.":[7],"speech-to-speech":[8],"translation.":[9],"However,":[10],"in":[11,101,117],"cross-language":[12,64,138],"adaptation,":[14,136],"a":[15,36],"common":[16],"phoneme":[17,40,113],"set,":[18],"assumed":[19],"to":[20,45,71,77,94],"be":[21,78],"used":[22,55],"by":[23],"different":[24,82,102],"speakers":[25],"of":[26,119,140],"the":[27,46,96,112,137,141],"same":[28],"language,":[29],"does":[30],"not":[31],"exist":[32],"any":[33],"longer.":[34],"Instead,":[35],"nearest":[37],"neighbor":[38],"based":[39],"mapping":[41,62,110,114],"from":[42],"one":[43],"language":[44],"other":[47],"been":[49],"adopted.":[50],"In":[51,132],"this":[52],"study,":[53],"we":[54],"our":[56],"recently":[57],"proposed":[58],"sub-phonemic":[59,67],"HMM":[60,68],"state":[61,109],"for":[63],"adaptations.":[65],"The":[66],"states,":[69],"due":[70],"their":[72],"phonetic":[73],"segment":[74],"nature,":[75],"tend":[76],"more":[79],"sharable":[80],"across":[81],"languages":[83],"than":[84],"phonemes.":[85],"Kullback-Leibler":[86],"divergence,":[87],"an":[88],"information-theoretic":[89],"measure,":[90],"is":[91,144],"chosen":[92],"here":[93],"measure":[95],"similarity":[97],"between":[98],"given":[99],"states":[100],"languages.":[103],"Experimental":[104],"results":[105],"show":[106],"that":[107],"new":[108,142],"outperforms":[111],"baseline":[115],"system":[116],"terms":[118],"three":[120],"objective":[121],"measures:":[122],"log":[123],"spectral":[124],"distance,":[125],"F0":[126,130],"error":[128],"and":[129],"correlations.":[131],"comparing":[133],"with":[134],"intra-language":[135],"result":[139],"algorithm":[143],"also":[145],"fairly":[146],"decent.":[147]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}