{"id":"https://openalex.org/W4392904511","doi":"https://doi.org/10.1109/icassp48485.2024.10447815","title":"Improving Language Model-Based Zero-Shot Text-to-Speech Synthesis with Multi-Scale Acoustic Prompts","display_name":"Improving Language Model-Based Zero-Shot Text-to-Speech Synthesis with Multi-Scale Acoustic Prompts","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904511","doi":"https://doi.org/10.1109/icassp48485.2024.10447815"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447815","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447815","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5103014224","display_name":"Shun Lei","orcid":"https://orcid.org/0000-0003-3597-3913"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shun Lei","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen","Shenzhen International Graduate School, Tsinghua University, Shenzhen"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I4210114105"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749226","display_name":"Yixuan Zhou","orcid":"https://orcid.org/0009-0002-6363-891X"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I53486688","display_name":"Skyworks Solutions (United States)","ror":"https://ror.org/02jymes45","country_code":"US","type":"company","lineage":["https://openalex.org/I53486688"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yixuan Zhou","raw_affiliation_strings":["Skywork AI PTE. LTD.,Beijing","Tsinghua University,Shenzhen International Graduate School,Shenzhen","Shenzhen International Graduate School, Tsinghua University, Shenzhen"],"affiliations":[{"raw_affiliation_string":"Skywork AI PTE. LTD.,Beijing","institution_ids":["https://openalex.org/I53486688"]},{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I4210114105"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101849127","display_name":"Liyang Chen","orcid":"https://orcid.org/0000-0001-6985-8281"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liyang Chen","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen","Shenzhen International Graduate School, Tsinghua University, Shenzhen"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I4210114105"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100632528","display_name":"Dan Luo","orcid":"https://orcid.org/0000-0002-7555-0045"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Luo","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen","Shenzhen International Graduate School, Tsinghua University, Shenzhen"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I4210114105"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen","The Chinese University of Hong Kong","Shenzhen International Graduate School, Tsinghua University, Shenzhen"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I4210114105"]},{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025119324","display_name":"Xixin Wu","orcid":"https://orcid.org/0000-0001-9543-1572"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xixin Wu","raw_affiliation_strings":["The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083463839","display_name":"Shiyin Kang","orcid":"https://orcid.org/0000-0001-8304-5260"},"institutions":[{"id":"https://openalex.org/I53486688","display_name":"Skyworks Solutions (United States)","ror":"https://ror.org/02jymes45","country_code":"US","type":"company","lineage":["https://openalex.org/I53486688"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiyin Kang","raw_affiliation_strings":["Skywork AI PTE. LTD.,Beijing","Skywork AI PTE. LTD., Beijing"],"affiliations":[{"raw_affiliation_string":"Skywork AI PTE. LTD.,Beijing","institution_ids":["https://openalex.org/I53486688"]},{"raw_affiliation_string":"Skywork AI PTE. LTD., Beijing","institution_ids":["https://openalex.org/I53486688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100744501","display_name":"Tao Jiang","orcid":"https://orcid.org/0000-0001-9116-2635"},"institutions":[{"id":"https://openalex.org/I53486688","display_name":"Skyworks Solutions (United States)","ror":"https://ror.org/02jymes45","country_code":"US","type":"company","lineage":["https://openalex.org/I53486688"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Jiang","raw_affiliation_strings":["Skywork AI PTE. LTD.,Beijing","Skywork AI PTE. LTD., Beijing"],"affiliations":[{"raw_affiliation_string":"Skywork AI PTE. LTD.,Beijing","institution_ids":["https://openalex.org/I53486688"]},{"raw_affiliation_string":"Skywork AI PTE. LTD., Beijing","institution_ids":["https://openalex.org/I53486688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114136994","display_name":"Yahui Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I53486688","display_name":"Skyworks Solutions (United States)","ror":"https://ror.org/02jymes45","country_code":"US","type":"company","lineage":["https://openalex.org/I53486688"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yahui Zhou","raw_affiliation_strings":["Skywork AI PTE. LTD.,Beijing","Tsinghua University,Shenzhen International Graduate School,Shenzhen","Skywork AI PTE. LTD., Beijing"],"affiliations":[{"raw_affiliation_string":"Skywork AI PTE. LTD.,Beijing","institution_ids":["https://openalex.org/I53486688"]},{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I4210114105"]},{"raw_affiliation_string":"Skywork AI PTE. LTD., Beijing","institution_ids":["https://openalex.org/I53486688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101319197","display_name":"Yuxing Han","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxing Han","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen","Shenzhen International Graduate School, Tsinghua University, Shenzhen"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I4210114105"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102225156","display_name":"Helen Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5103014224"],"corresponding_institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I4210114105","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.6632,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72176486,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"12662","last_page":"12666"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9973999857902527,"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":0.9947999715805054,"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/naturalness","display_name":"Naturalness","score":0.7751446962356567},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7726354002952576},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7249568104743958},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.6828010082244873},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5979841351509094},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5368813276290894},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5128434300422668},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4485694468021393},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3438766598701477},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.22907695174217224}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7751446962356567},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7726354002952576},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7249568104743958},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.6828010082244873},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5979841351509094},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5368813276290894},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5128434300422668},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4485694468021393},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3438766598701477},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.22907695174217224},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447815","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447815","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4099999964237213}],"awards":[{"id":"https://openalex.org/G2603945996","display_name":null,"funder_award_id":"62076144","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335869","display_name":"National Social Science Fund of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2808706139","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2972574864","https://openalex.org/W3015826515","https://openalex.org/W3016159759","https://openalex.org/W3095199334","https://openalex.org/W3095545636","https://openalex.org/W3174758275","https://openalex.org/W3197704090","https://openalex.org/W3215615641","https://openalex.org/W4292779060","https://openalex.org/W4297841574","https://openalex.org/W4307323391","https://openalex.org/W4313679638","https://openalex.org/W4366460484","https://openalex.org/W4379924545","https://openalex.org/W4381786045","https://openalex.org/W4385486424","https://openalex.org/W4390075359","https://openalex.org/W6752888775","https://openalex.org/W6755135894","https://openalex.org/W6778823374","https://openalex.org/W6778883912","https://openalex.org/W6790220310","https://openalex.org/W6796730497","https://openalex.org/W6805710207","https://openalex.org/W6848735303","https://openalex.org/W6851724922","https://openalex.org/W6852870047"],"related_works":["https://openalex.org/W1524071955","https://openalex.org/W2500371832","https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W2535215250"],"abstract_inverted_index":{"Zero-shot":[0],"text-to-speech":[1],"(TTS)":[2],"synthesis":[3],"aims":[4],"to":[5,65,96,122,161],"clone":[6,66],"any":[7],"unseen":[8,48],"speaker\u2019s":[9],"voice":[10],"without":[11],"adaptation":[12,38],"parameters.":[13],"By":[14],"quantizing":[15],"speech":[16],"waveform":[17],"into":[18],"discrete":[19],"acoustic":[20,44,59,83,118],"tokens":[21,25],"and":[22,133,150,153],"modeling":[23],"these":[24],"with":[26,40,80],"the":[27,55,58,81,98,103,106,124,127,131],"language":[28,31,88],"model,":[29],"recent":[30],"model-based":[32],"TTS":[33,78],"models":[34],"show":[35,139],"zero-shot":[36,77],"speaker":[37,151],"capabilities":[39],"only":[41],"a":[42,75,87,115,162],"3-second":[43],"prompt":[45,108,129],"of":[46,57,110,148],"an":[47],"speaker.":[49],"However,":[50],"they":[51],"are":[52],"limited":[53],"by":[54,158],"length":[56],"prompt,":[60],"which":[61],"makes":[62],"it":[63],"difficult":[64],"personal":[67,99],"speaking":[68,100],"style.":[69],"In":[70],"this":[71],"paper,":[72],"we":[73],"propose":[74],"novel":[76],"model":[79,123],"multi-scale":[82],"prompts":[84],"based":[85,117],"on":[86],"model.":[89],"A":[90],"speaker-aware":[91],"text":[92],"encoder":[93],"is":[94,120],"proposed":[95,142],"learn":[97],"style":[101,107,164],"at":[102,130],"phoneme-level":[104],"from":[105,126],"consisting":[109],"multiple":[111],"sentences.":[112],"Following":[113],"that,":[114],"VALL-E":[116],"decoder":[119],"utilized":[121],"timbre":[125,128],"frame-level":[132],"generate":[134],"speech.":[135],"The":[136],"experimental":[137],"results":[138],"that":[140],"our":[141],"method":[143],"outperforms":[144],"baselines":[145],"in":[146],"terms":[147],"naturalness":[149],"similarity,":[152],"can":[154],"achieve":[155],"better":[156],"performance":[157],"scaling":[159],"out":[160],"longer":[163],"prompt<sup":[165],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[166],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}