{"id":"https://openalex.org/W4391021679","doi":"https://doi.org/10.1109/asru57964.2023.10389772","title":"Promptspeaker: Speaker Generation Based on Text Descriptions","display_name":"Promptspeaker: Speaker Generation Based on Text Descriptions","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021679","doi":"https://doi.org/10.1109/asru57964.2023.10389772"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389772","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389772","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5060467975","display_name":"Yongmao Zhang","orcid":"https://orcid.org/0009-0000-0526-5778"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yongmao Zhang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP&#x0040;NPU) School of Computer Science,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP&#x0040;NPU) School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Guanghou Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanghou Liu","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP&#x0040;NPU) School of Computer Science,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP&#x0040;NPU) School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100678947","display_name":"Yi Lei","orcid":"https://orcid.org/0000-0003-1105-3258"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Lei","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP&#x0040;NPU) School of Computer Science,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP&#x0040;NPU) School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104124393","display_name":"Yunlin Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunlin Chen","raw_affiliation_strings":["Shanghai Mobvoi Information Technology Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Shanghai Mobvoi Information Technology Co., Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100917169","display_name":"Hao Yin","orcid":"https://orcid.org/0009-0008-5127-5764"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Yin","raw_affiliation_strings":["Shanghai Mobvoi Information Technology Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Shanghai Mobvoi Information Technology Co., Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP&#x0040;NPU) School of Computer Science,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP&#x0040;NPU) School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100782897","display_name":"Zhifei Li","orcid":"https://orcid.org/0000-0003-0443-0094"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhifei Li","raw_affiliation_strings":["Shanghai Mobvoi Information Technology Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Shanghai Mobvoi Information Technology Co., Ltd","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5060467975"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":1.0306,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.82092164,"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":"1","last_page":"7"},"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/T11309","display_name":"Music and Audio Processing","score":0.9965999722480774,"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":0.9955000281333923,"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":0.7382135391235352},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5651450157165527},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5153874158859253},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4355507493019104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40754061937332153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7382135391235352},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5651450157165527},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5153874158859253},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4355507493019104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40754061937332153}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389772","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389772","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2395011401","https://openalex.org/W3163132306","https://openalex.org/W3174758275","https://openalex.org/W3178584958","https://openalex.org/W3198123658","https://openalex.org/W3198533616","https://openalex.org/W4224035735","https://openalex.org/W4224929761","https://openalex.org/W4296069283","https://openalex.org/W4318752004","https://openalex.org/W4372340947","https://openalex.org/W4375869257","https://openalex.org/W4385822787","https://openalex.org/W4398152753","https://openalex.org/W6750489868","https://openalex.org/W6752910514","https://openalex.org/W6763832098","https://openalex.org/W6796464841","https://openalex.org/W6796730497","https://openalex.org/W6805710207","https://openalex.org/W6809885388","https://openalex.org/W6847037835","https://openalex.org/W6847154022","https://openalex.org/W6849109464","https://openalex.org/W6849798658"],"related_works":["https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149","https://openalex.org/W2368768466"],"abstract_inverted_index":{"Recently,":[0],"text-guided":[1,35],"content":[2],"generation":[3,28,37],"has":[4,121],"received":[5],"extensive":[6],"attention.":[7],"In":[8],"this":[9,68],"work,":[10],"we":[11,31],"explore":[12],"the":[13,26,53,62,80,88,93,98,110,117,127,136],"possibility":[14],"of":[15,41],"text":[16,22,63],"description-based":[17],"speaker":[18,27,36,85,99,119,128],"generation,":[19],"i.e.,":[20],"using":[21],"prompts":[23],"to":[24,70],"control":[25],"process.":[29],"Specifically,":[30],"propose":[32],"PromptSpeaker,":[33],"a":[34,42,45,49,57,72,84],"system.":[38],"PromptSpeaker":[39,104],"consists":[40],"prompt":[43,54],"encoder,":[44],"zero-shot":[46,89],"VITS,":[47],"and":[48,65,87,116],"Glow":[50,76],"model,":[51],"where":[52],"encoder":[55],"predicts":[56],"prior":[58],"distribution":[59,69],"based":[60,96],"on":[61,97,135],"description":[64],"samples":[66,132],"from":[67,109],"obtain":[71],"semantic":[73,81],"representation.":[74,100],"The":[75],"model":[77],"subsequently":[78],"converts":[79],"representation":[82],"into":[83],"representation,":[86],"VITS":[90],"finally":[91],"synthesizes":[92],"speaker\u2019s":[94],"voice":[95,120],"We":[101],"verify":[102],"that":[103],"can":[105],"generate":[106],"speakers":[107],"new":[108],"training":[111],"set":[112],"by":[113],"objective":[114],"metrics,":[115],"synthetic":[118],"reasonable":[122],"subjective":[123],"matching":[124],"quality":[125],"with":[126],"prompt.":[129],"Our":[130],"audio":[131],"are":[133],"available":[134],"demo":[137],"website":[138],"<sup":[139,143],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[140,144],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[141,145],".":[142],"Demo:":[146],"https://promptspeaker.github.io/demo/":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}