{"id":"https://openalex.org/W1797093408","doi":"https://doi.org/10.1109/icassp.2003.1198829","title":"Trainable Cantonese/English dual language speech synthesis system","display_name":"Trainable Cantonese/English dual language speech synthesis system","publication_year":2003,"publication_date":"2003-11-21","ids":{"openalex":"https://openalex.org/W1797093408","doi":"https://doi.org/10.1109/icassp.2003.1198829","mag":"1797093408"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1198829","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198829","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":"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/A5100674775","display_name":"Haiping Li","orcid":"https://orcid.org/0000-0002-2503-2709"},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiping Li","raw_affiliation_strings":["IBM China Research Laboratory, Beijing, China","IBM China Research Lab, BeiJing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM China Research Laboratory, Beijing, China","institution_ids":["https://openalex.org/I4210126794"]},{"raw_affiliation_string":"IBM China Research Lab, BeiJing, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041719965","display_name":"Fangxin Chen","orcid":"https://orcid.org/0000-0002-9444-4141"},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangxin Chen","raw_affiliation_strings":["IBM China Research Laboratory, Beijing, China","IBM China Research Lab, BeiJing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM China Research Laboratory, Beijing, China","institution_ids":["https://openalex.org/I4210126794"]},{"raw_affiliation_string":"IBM China Research Lab, BeiJing, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066535698","display_name":"Li Shen","orcid":"https://orcid.org/0000-0001-6178-1427"},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Qin Shen","raw_affiliation_strings":["IBM China Research Laboratory, Beijing, China","IBM China Research Lab, BeiJing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM China Research Laboratory, Beijing, China","institution_ids":["https://openalex.org/I4210126794"]},{"raw_affiliation_string":"IBM China Research Lab, BeiJing, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110378704","display_name":"Xi Jun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Jun Ma","raw_affiliation_strings":["IBM China Research Laboratory, Beijing, China","IBM China Research Lab, BeiJing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM China Research Laboratory, Beijing, China","institution_ids":["https://openalex.org/I4210126794"]},{"raw_affiliation_string":"IBM China Research Lab, BeiJing, China","institution_ids":["https://openalex.org/I4210126794"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.21560575,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"508"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9851999878883362,"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":0.9851999878883362,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.958299994468689,"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":0.9399999976158142,"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":0.8140243291854858},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.7405058145523071},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.643191397190094},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.6340327262878418},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6232998371124268},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6018911004066467},{"id":"https://openalex.org/keywords/intonation","display_name":"Intonation (linguistics)","score":0.5656350255012512},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5527523756027222},{"id":"https://openalex.org/keywords/tone","display_name":"Tone (literature)","score":0.5224884152412415},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5139205455780029},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.511354386806488},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.47665315866470337},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4749198853969574},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.26442718505859375},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0913814902305603}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8140243291854858},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7405058145523071},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.643191397190094},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.6340327262878418},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6232998371124268},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6018911004066467},{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.5656350255012512},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5527523756027222},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.5224884152412415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5139205455780029},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.511354386806488},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.47665315866470337},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4749198853969574},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.26442718505859375},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0913814902305603},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2003.1198829","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198829","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W44584094","https://openalex.org/W75668230","https://openalex.org/W1580270414","https://openalex.org/W6601815149","https://openalex.org/W6603100307"],"related_works":["https://openalex.org/W2396586136","https://openalex.org/W1965454423","https://openalex.org/W2028501571","https://openalex.org/W2052542215","https://openalex.org/W2036564641","https://openalex.org/W1505084104","https://openalex.org/W2599935372","https://openalex.org/W1966171935","https://openalex.org/W1927421023","https://openalex.org/W10581632"],"abstract_inverted_index":{"The":[0,32],"paper":[1],"introduces":[2],"a":[3,44,69],"Cantonese/English":[4],"dual":[5],"language":[6],"text":[7],"to":[8,25,126],"speech":[9,27,60,83],"(TTS)":[10],"system.":[11],"It":[12],"was":[13,73],"developed":[14],"on":[15],"IBM's":[16],"trainable":[17,22],"TTS":[18],"technology,":[19],"which":[20,48],"uses":[21],"statistical":[23],"models":[24],"automate":[26],"data":[28],"processing":[29,85],"and":[30,34,38,54,58,78,93],"selection.":[31],"Cantonese":[33,57,108],"English":[35,59],"phonological,":[36],"syntactic":[37],"prosodic":[39],"rules":[40],"were":[41],"built":[42],"into":[43,80],"dual-language":[45],"delta":[46,82],"module,":[47],"processes":[49],"the":[50,66,76,81,87,97,100],"mixed-language":[51],"input":[52],"accordingly":[53],"generates":[55],"mixed":[56],"with":[61,106],"coherent":[62],"prosody.":[63],"To":[64],"approximate":[65],"speaker's":[67],"characteristics,":[68],"speaker":[70],"prosody":[71],"profile":[72],"extracted":[74],"from":[75],"dataset":[77],"incorporated":[79],"rule":[84],"for":[86,119],"enhancement":[88],"of":[89,99],"duration,":[90],"lexical":[91],"tone":[92],"intonation":[94],"prediction.":[95],"In":[96],"selection":[98],"concatenative":[101],"unit":[102],"set,":[103],"we":[104],"experimented":[105],"different":[107],"syllable":[109],"decomposition":[110],"schemes.":[111],"Though":[112],"this":[113],"system":[114],"is":[115],"currently":[116],"only":[117],"implemented":[118],"Cantonese,":[120],"it":[121],"can":[122],"be":[123],"easily":[124],"adapted":[125],"other":[127],"tonal":[128],"languages.":[129]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}