{"id":"https://openalex.org/W4224931727","doi":"https://doi.org/10.1109/icassp43922.2022.9746914","title":"Improving Cross-Lingual Speech Synthesis with Triplet Training Scheme","display_name":"Improving Cross-Lingual Speech Synthesis with Triplet Training Scheme","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224931727","doi":"https://doi.org/10.1109/icassp43922.2022.9746914"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746914","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746914","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5088838965","display_name":"Jianhao Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jianhao Ye","raw_affiliation_strings":["Ximalaya Inc.,China","Ximalaya Inc., China"],"affiliations":[{"raw_affiliation_string":"Ximalaya Inc.,China","institution_ids":[]},{"raw_affiliation_string":"Ximalaya Inc., China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110823442","display_name":"Hongbin Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongbin Zhou","raw_affiliation_strings":["Ximalaya Inc.,China","Ximalaya Inc., China"],"affiliations":[{"raw_affiliation_string":"Ximalaya Inc.,China","institution_ids":[]},{"raw_affiliation_string":"Ximalaya Inc., China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070507407","display_name":"Zhiba Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiba Su","raw_affiliation_strings":["Ximalaya Inc.,China","Ximalaya Inc., China"],"affiliations":[{"raw_affiliation_string":"Ximalaya Inc.,China","institution_ids":[]},{"raw_affiliation_string":"Ximalaya Inc., China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069977860","display_name":"Wendi He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wendi He","raw_affiliation_strings":["Ximalaya Inc.,China","Ximalaya Inc., China"],"affiliations":[{"raw_affiliation_string":"Ximalaya Inc.,China","institution_ids":[]},{"raw_affiliation_string":"Ximalaya Inc., China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087378505","display_name":"Kaimeng Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaimeng Ren","raw_affiliation_strings":["Ximalaya Inc.,China","Ximalaya Inc., China"],"affiliations":[{"raw_affiliation_string":"Ximalaya Inc.,China","institution_ids":[]},{"raw_affiliation_string":"Ximalaya Inc., China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103050255","display_name":"Lin Li","orcid":"https://orcid.org/0000-0003-4410-7064"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["Ximalaya Inc.,China","Ximalaya Inc., China"],"affiliations":[{"raw_affiliation_string":"Ximalaya Inc.,China","institution_ids":[]},{"raw_affiliation_string":"Ximalaya Inc., China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100618443","display_name":"Heng Lu","orcid":"https://orcid.org/0009-0009-9236-8825"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heng Lu","raw_affiliation_strings":["Ximalaya Inc.,China","Ximalaya Inc., China"],"affiliations":[{"raw_affiliation_string":"Ximalaya Inc.,China","institution_ids":[]},{"raw_affiliation_string":"Ximalaya Inc., China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5088838965"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4185,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.5572163,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6072","last_page":"6076"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9944999814033508,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9912999868392944,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8979825973510742},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.8011443614959717},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7882963418960571},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7671058177947998},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6792541146278381},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5858595967292786},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.4342291057109833},{"id":"https://openalex.org/keywords/first-language","display_name":"First language","score":0.4164084196090698},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40398722887039185},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38247793912887573},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17752134799957275}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8979825973510742},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8011443614959717},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7882963418960571},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7671058177947998},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6792541146278381},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5858595967292786},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.4342291057109833},{"id":"https://openalex.org/C171041071","wikidata":"https://www.wikidata.org/wiki/Q36870","display_name":"First language","level":2,"score":0.4164084196090698},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40398722887039185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38247793912887573},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17752134799957275},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746914","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746914","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"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":26,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2096733369","https://openalex.org/W2748238740","https://openalex.org/W2964002616","https://openalex.org/W2964243274","https://openalex.org/W2972473628","https://openalex.org/W3016139610","https://openalex.org/W3033411150","https://openalex.org/W3092028330","https://openalex.org/W3094785744","https://openalex.org/W3097032879","https://openalex.org/W3097538987","https://openalex.org/W3135619128","https://openalex.org/W3161436426","https://openalex.org/W3197186640","https://openalex.org/W3197186969","https://openalex.org/W4287599683","https://openalex.org/W6631362777","https://openalex.org/W6768830310","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6785505132","https://openalex.org/W6791845930","https://openalex.org/W6800444139","https://openalex.org/W6801051914","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2500371832","https://openalex.org/W2079655441","https://openalex.org/W1524071955","https://openalex.org/W2912293245","https://openalex.org/W1604114751","https://openalex.org/W4252942110","https://openalex.org/W2032941915","https://openalex.org/W2075706796","https://openalex.org/W2549308614","https://openalex.org/W3018584924"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,12,39,136],"cross-lingual":[3,32,57,116,144],"text-to-speech":[4],"(TTS)":[5],"made":[6],"it":[7],"possible":[8],"to":[9,16,54,67,95],"synthesize":[10],"speech":[11,33,93],"a":[13,17,24,48,113],"language":[14],"foreign":[15,92],"monolingual":[18],"speaker.":[19],"However,":[20],"there":[21],"is":[22,52],"still":[23],"large":[25],"gap":[26],"between":[27],"the":[28,56,87,90,98,104,124,130,142],"pronunciation":[29,58,88],"of":[30,36,41,89,141],"generated":[31],"and":[34,43,64,119,126,139],"that":[35],"native":[37,99],"speakers":[38],"terms":[40],"naturalness":[42,140],"intelligibility.":[44],"In":[45],"this":[46],"paper,":[47],"triplet":[49,80],"training":[50],"scheme":[51],"proposed":[53,131],"enhance":[55],"by":[59],"allowing":[60],"previously":[61],"unseen":[62],"content":[63],"speaker":[65],"combinations":[66],"be":[68],"seen":[69],"during":[70,82],"training.":[71],"Proposed":[72],"method":[73,132],"introduces":[74],"an":[75],"extra":[76],"fine-tune":[77],"stage":[78],"with":[79],"loss":[81],"training,":[83],"which":[84],"efficiently":[85],"draws":[86],"synthesized":[91,143],"closer":[94],"those":[96],"from":[97],"anchor":[100],"speaker,":[101],"while":[102],"preserving":[103],"non-native":[105],"speaker\u2019s":[106],"timbre.":[107],"Experiments":[108],"are":[109],"conducted":[110],"based":[111],"on":[112],"state-of-the-art":[114],"baseline":[115],"TTS":[117],"system":[118],"its":[120],"enhanced":[121],"variants.":[122],"All":[123],"objective":[125],"subjective":[127],"evaluations":[128],"show":[129],"brings":[133],"significant":[134],"improvement":[135],"both":[137],"intelligibility":[138],"speech.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}
