{"id":"https://openalex.org/W2123140629","doi":"https://doi.org/10.1109/icassp.2008.4518691","title":"A cross-language state mapping approach to bilingual (Mandarin-English) TTS","display_name":"A cross-language state mapping approach to bilingual (Mandarin-English) TTS","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2123140629","doi":"https://doi.org/10.1109/icassp.2008.4518691","mag":"2123140629"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518691","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518691","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 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/A5068810492","display_name":"Hui Liang","orcid":"https://orcid.org/0000-0001-6632-0929"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"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":"Hui Liang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","School of Information Security Engineering, Shanghai Jiaotong University, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"School of Information Security Engineering, Shanghai Jiaotong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"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":"middle","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"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085695760","display_name":"Gongshen Liu","orcid":"https://orcid.org/0000-0001-5194-1570"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gongshen Liu","raw_affiliation_strings":["School of Information Security Engineering, Shanghai Jiaotong University, China"],"affiliations":[{"raw_affiliation_string":"School of Information Security Engineering, Shanghai Jiaotong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5068810492"],"corresponding_institution_ids":["https://openalex.org/I183067930","https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":3.5387,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.93220339,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"e85 d","issue":null,"first_page":"4641","last_page":"4644"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965999722480774,"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":0.9965999722480774,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9958000183105469,"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/T10860","display_name":"Speech and Audio Processing","score":0.9915000200271606,"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":0.8195285797119141},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.6835005283355713},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.604870617389679},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5330568552017212},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5055751800537109},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4838932454586029},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.47725722193717957},{"id":"https://openalex.org/keywords/first-language","display_name":"First language","score":0.44898656010627747},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.4447178542613983},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.33877599239349365},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.24810534715652466}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8195285797119141},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.6835005283355713},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.604870617389679},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5330568552017212},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5055751800537109},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4838932454586029},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.47725722193717957},{"id":"https://openalex.org/C171041071","wikidata":"https://www.wikidata.org/wiki/Q36870","display_name":"First language","level":2,"score":0.44898656010627747},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.4447178542613983},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.33877599239349365},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24810534715652466},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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":1,"locations":[{"id":"doi:10.1109/icassp.2008.4518691","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518691","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"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/W40001856","https://openalex.org/W129217914","https://openalex.org/W143368150","https://openalex.org/W1499275966","https://openalex.org/W1512429158","https://openalex.org/W1607515033","https://openalex.org/W2099531983","https://openalex.org/W2146927751","https://openalex.org/W2154920538","https://openalex.org/W2167127461","https://openalex.org/W2395432258","https://openalex.org/W2398350133","https://openalex.org/W2398462115","https://openalex.org/W6601527497","https://openalex.org/W6601627100","https://openalex.org/W6605232188","https://openalex.org/W6605825178","https://openalex.org/W6630838124","https://openalex.org/W6674798237","https://openalex.org/W6711946875","https://openalex.org/W6712471867","https://openalex.org/W6712869911"],"related_works":["https://openalex.org/W1540615732","https://openalex.org/W3115948027","https://openalex.org/W2405110677","https://openalex.org/W4387323809","https://openalex.org/W4200068392","https://openalex.org/W2772686614","https://openalex.org/W2031265216","https://openalex.org/W2793090466","https://openalex.org/W2036933852","https://openalex.org/W2152945827"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,19,25,40,55,77,154],"cross-language":[3],"state":[4,29],"mapping":[5,30],"approach":[6],"to":[7,65],"HMM-based":[8],"bilingual":[9,20,119],"TTS.":[10],"Two":[11,143],"language-dependent":[12],"decision":[13,37],"trees":[14],"are":[15],"built":[16],"first":[17],"with":[18,153],"speech":[21,75,122,138,149],"database":[22],"recorded":[23],"by":[24,45,76,88,104,123,126],"single":[26],"speaker.":[27,129],"A":[28],"for":[31],"every":[32],"leaf":[33,49,69,97],"node":[34,50],"in":[35,51,94,136],"the":[36,47,52,67,89,95,106,140],"tree":[38,53],"of":[39,54,139,159,165],"target":[41,73,109,141],"language":[42,74],"is":[43,63,134],"created":[44],"finding":[46],"nearest":[48,68],"source":[56,107],"language.":[57,142],"Kullback-Leibler":[58],"divergence":[59],"between":[60],"two":[61],"distributions":[62],"used":[64],"find":[66,84],"node.":[70],"To":[71],"synthesize":[72,118],"monolingual,":[78],"(source":[79,91],"language)":[80,92],"speaker's":[81],"voice,":[82],"we":[83,116],"HMM":[85],"parameters":[86],"trained":[87,125],"monolingual":[90,128],"speaker":[93],"mapped":[96],"nodes.":[98],"Similar":[99],"mappings":[100],"can":[101,117],"be":[102],"constructed":[103],"reversing":[105],"and":[108,161],"languages.":[110],"With":[111],"these":[112],"bi-directional":[113],"cross-lingual":[114],"mappings,":[115],"or":[120],"mixed-code":[121],"HMMs":[124],"any":[127],"High":[130],"voice":[131],"(speaker)":[132],"similarity":[133],"preserved":[135],"synthesized":[137,147],"perceptual":[144],"tests":[145],"on":[146],"Mandarin":[148],"confirms":[150],"high":[151],"intelligibility":[152],"Chinese":[155],"character":[156],"transcription":[157],"accuracy":[158],"92.1%":[160],"an":[162],"MOS":[163],"score":[164],"3.08.":[166]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
