{"id":"https://openalex.org/W2099531983","doi":"https://doi.org/10.1109/icassp.2003.1198768","title":"Microsoft Mulan - a bilingual TTS system","display_name":"Microsoft Mulan - a bilingual TTS system","publication_year":2003,"publication_date":"2003-11-21","ids":{"openalex":"https://openalex.org/W2099531983","doi":"https://doi.org/10.1109/icassp.2003.1198768","mag":"2099531983"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1198768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198768","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"},"type":"conference-paper","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/A5104229610","display_name":"Min Chu","orcid":null},"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":"Min Chu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000760367","display_name":"Peng Hu","orcid":"https://orcid.org/0000-0003-3478-0300"},"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":"Hu Peng","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702069","display_name":"Yong Zhao","orcid":"https://orcid.org/0000-0002-7062-456X"},"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":"Yong Zhao","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033269202","display_name":"Zheng-Yu Niu","orcid":null},"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":"Zhengyu Niu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087298985","display_name":"Eric Chang","orcid":"https://orcid.org/0000-0002-9678-5994"},"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":"E. Chang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":11.3266,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":{"value":0.98580442,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"264"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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/T12031","display_name":"Speech and dialogue systems","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7217319011688232},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5932321548461914},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.552808940410614},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.5321224331855774},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.4987940788269043},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4917431175708771},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41112056374549866},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4102975130081177},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.34238922595977783},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32191258668899536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7217319011688232},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5932321548461914},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.552808940410614},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.5321224331855774},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.4987940788269043},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4917431175708771},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41112056374549866},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4102975130081177},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.34238922595977783},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32191258668899536},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2003.1198768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198768","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.187.8856","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.187.8856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/en-us/groups/speech/01-00264.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W71082305","https://openalex.org/W75668230","https://openalex.org/W160640889","https://openalex.org/W164706226","https://openalex.org/W1499275966","https://openalex.org/W1847897332","https://openalex.org/W1912504566","https://openalex.org/W2106564373","https://openalex.org/W2119174565","https://openalex.org/W2130529984","https://openalex.org/W2137401844","https://openalex.org/W2149081372","https://openalex.org/W2394962911","https://openalex.org/W2398649184","https://openalex.org/W2428180336","https://openalex.org/W4302326871","https://openalex.org/W6603100307","https://openalex.org/W6606512584","https://openalex.org/W6606687067","https://openalex.org/W6629972488","https://openalex.org/W6638909738","https://openalex.org/W6677898495","https://openalex.org/W6712526093"],"related_works":["https://openalex.org/W2222951281","https://openalex.org/W2272290179","https://openalex.org/W156219719","https://openalex.org/W2068412075","https://openalex.org/W2514064218","https://openalex.org/W2094188777","https://openalex.org/W2132658536","https://openalex.org/W2112609279","https://openalex.org/W1581825163","https://openalex.org/W1483316057"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,81],"bilingual":[4],"text-to-speech":[5],"(TTS)":[6],"system,":[7],"Microsoft":[8],"Mulan,":[9],"which":[10,18,87],"switches":[11],"between":[12],"Mandarin":[13],"and":[14,17,41,74,94],"English":[15],"smoothly":[16],"maintains":[19],"the":[20,32,35,42,64,69,75,84,91,96,99,110,119],"sentence":[21],"level":[22],"intonation":[23],"even":[24,62],"for":[25],"mixed-lingual":[26],"texts.":[27],"Mulan":[28,51,79,123],"is":[29,52,57,66],"constructed":[30],"on":[31],"basis":[33],"of":[34,50,98],"Soft":[36],"Prediction":[37],"Only":[38],"prosodic":[39],"strategy":[40],"Prosodic-Constraint":[43],"Orient":[44],"unit-selection":[45,48],"strategy.":[46],"The":[47,103],"module":[49],"shared":[53],"across":[54],"languages.":[55],"It":[56],"insensitive":[58],"to":[59,90,114],"language":[60],"identity,":[61],"though":[63],"syllable":[65],"used":[67],"as":[68],"smallest":[70],"unit":[71],"in":[72,77],"Mandarin,":[73],"phoneme":[76],"English.":[78],"has":[80],"unique":[82],"module,":[83,86],"language-dispatching":[85],"dispatches":[88],"texts":[89,105],"language-specific":[92],"front-ends":[93,101],"merges":[95],"outputs":[97],"two":[100],"together.":[102],"mixed":[104],"are":[106],"\"uttered\"":[107],"out":[108],"with":[109,122],"same":[111],"voice.":[112],"According":[113],"our":[115],"informal":[116],"listening":[117],"test,":[118],"speech":[120],"synthesized":[121],"sounds":[124],"quite":[125],"natural.":[126],"Sample":[127],"waves":[128],"can":[129],"be":[130],"heard":[131],"at:":[132],"http://research.microsoft.com/-echang/proiects/tts/mulan.htm.":[133]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
