{"id":"https://openalex.org/W2114010348","doi":"https://doi.org/10.1109/tasl.2009.2015708","title":"A Cross-Language State Sharing and Mapping Approach to Bilingual (Mandarin\u2013English) TTS","display_name":"A Cross-Language State Sharing and Mapping Approach to Bilingual (Mandarin\u2013English) TTS","publication_year":2009,"publication_date":"2009-07-01","ids":{"openalex":"https://openalex.org/W2114010348","doi":"https://doi.org/10.1109/tasl.2009.2015708","mag":"2114010348"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2009.2015708","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2009.2015708","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/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":true,"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":"middle","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"]},{"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":["CH","CN"],"is_corresponding":false,"raw_author_name":"Hui Liang","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland","Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"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":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100342006"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":8.1421,"has_fulltext":false,"cited_by_count":69,"citation_normalized_percentile":{"value":0.9754943,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"17","issue":"6","first_page":"1231","last_page":"1239"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9995999932289124,"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":0.9980999827384949,"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":0.787542462348938},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7629532814025879},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5664842128753662},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5563021302223206},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5021510124206543},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4948200583457947},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4810955226421356},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.44347310066223145},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4345023036003113},{"id":"https://openalex.org/keywords/first-language","display_name":"First language","score":0.4172983765602112},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3034380376338959},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1331554651260376},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.07186457514762878}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.787542462348938},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7629532814025879},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5664842128753662},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5563021302223206},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5021510124206543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4948200583457947},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4810955226421356},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.44347310066223145},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4345023036003113},{"id":"https://openalex.org/C171041071","wikidata":"https://www.wikidata.org/wiki/Q36870","display_name":"First language","level":2,"score":0.4172983765602112},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3034380376338959},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1331554651260376},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.07186457514762878},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2009.2015708","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2009.2015708","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W36870606","https://openalex.org/W88751538","https://openalex.org/W127087823","https://openalex.org/W129217914","https://openalex.org/W1512429158","https://openalex.org/W1519698338","https://openalex.org/W1538607601","https://openalex.org/W1607515033","https://openalex.org/W1963627370","https://openalex.org/W2049686551","https://openalex.org/W2099531983","https://openalex.org/W2100441082","https://openalex.org/W2123140629","https://openalex.org/W2146927751","https://openalex.org/W2154920538","https://openalex.org/W2395432258","https://openalex.org/W2398462115","https://openalex.org/W6601527497","https://openalex.org/W6605232188","https://openalex.org/W6630838124","https://openalex.org/W6674890362","https://openalex.org/W6711946875","https://openalex.org/W6712869911"],"related_works":["https://openalex.org/W2038801705","https://openalex.org/W2688184458","https://openalex.org/W2904846757","https://openalex.org/W175280642","https://openalex.org/W4200068392","https://openalex.org/W2772686614","https://openalex.org/W2036933852","https://openalex.org/W2793090466","https://openalex.org/W2152945827","https://openalex.org/W2015513221"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,44,80,121,128,150,210,231,235,254],"hidden":[3],"Markov":[4],"model":[5,164],"(HMM)-based":[6],"bilingual":[7,20,45,212],"(Mandarin":[8],"and":[9,39,58,187,199,261],"English)":[10],"text-to-speech":[11],"(TTS)":[12],"system":[13,25,78,92],"to":[14,96,125],"synthesize":[15],"natural":[16],"speech":[17,157,206,245,264],"for":[18,61,99,109,140],"given":[19],"text.":[21],"A":[22,47,132],"simple":[23],"baseline":[24,85,98],"consisting":[26],"of":[27,115,172,196,230,259,271],"two":[28,67],"independent":[29],"monolingual":[30,104,145,236],"HMM":[31,63,163],"synthesizers":[32],"is":[33,52,118,137,154,158,180,218,251],"built":[34],"first":[35],"from":[36,149,234],"corresponding":[37],"Mandarin":[38,101,156,244],"English":[40,174],"data":[41,148,207],"recorded":[42,147,208],"by":[43,55,89,120,209,226,253],"speaker.":[46,213,237],"new,":[48],"mixed":[49],"language":[50,152,224,233],"TTS":[51],"then":[53,159],"constructed":[54],"asking":[56],"language-independent":[57],"language-specific":[59],"questions":[60],"sharing":[62,74],"states":[64],"across":[65],"the":[66,76,84,90,97,162,167,173,183,193,197,205,221,228],"languages":[68,201],"in":[69,127,166,192,220],"decision-tree":[70],"based":[71],"clustering.":[72],"By":[73],"states,":[75],"new":[77,91],"has":[79],"smaller":[81],"footprint":[82],"than":[83],"system.":[86],"Speech":[87],"synthesized":[88,160,222,243],"sounds":[93],"very":[94],"similar":[95],"non-mixed,":[100],"or":[102],"English,":[103],"sentences":[105,225],"but":[106],"much":[107],"better":[108],"mixed-language":[110,116],"sentences.":[111],"This":[112],"higher":[113],"quality":[114,265],"output":[117],"confirmed":[119,252],"preference":[122],"score,":[123],"60.2%":[124],"39.8%,":[126],"subjective":[129],"listening":[130],"test.":[131],"cross-language":[133,141],"state":[134],"mapping":[135],"algorithm":[136],"further":[138],"proposed":[139],"synthesis":[142],"when":[143],"only":[144],"(English)":[146],"source":[151,198,232],"speaker":[153],"available.":[155],"with":[161,182,266],"parameters":[165],"nearest":[168,178],"neighbor":[169,179],"leaf":[170,190],"nodes":[171,191],"decision":[175,194],"tree.":[176],"The":[177],"measured":[181],"Kullback-Leibler":[184],"divergence":[185],"(KLD)":[186],"mappings":[188],"between":[189],"trees":[195],"target":[200,223],"are":[202],"established":[203],"via":[204],"different,":[211],"High":[214],"voice":[215],"(speaker)":[216],"similarity":[217],"preserved":[219],"using":[227],"recording":[229],"Perceptual":[238],"test":[239],"results":[240],"conducted":[241],"on":[242],"show":[246],"1)":[247],"high":[248],"intelligibility":[249],"which":[250],"Chinese":[255],"character":[256],"transcription":[257],"accuracy":[258],"92.1%":[260],"2)":[262],"decent":[263],"an":[267],"average":[268],"MOS":[269],"score":[270],"3.1.":[272]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":10}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}