{"id":"https://openalex.org/W4412945647","doi":"https://doi.org/10.18653/v1/2025.acl-long.346","title":"ControlSpeech: Towards Simultaneous and Independent Zero-shot Speaker Cloning and Zero-shot Language Style Control","display_name":"ControlSpeech: Towards Simultaneous and Independent Zero-shot Speaker Cloning and Zero-shot Language Style Control","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945647","doi":"https://doi.org/10.18653/v1/2025.acl-long.346"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.346","doi":"https://doi.org/10.18653/v1/2025.acl-long.346","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.346","pdf_url":"https://aclanthology.org/2025.acl-long.346.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2025.acl-long.346.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102904447","display_name":"Shengpeng Ji","orcid":"https://orcid.org/0000-0002-0129-4843","observed_orcids":["https://orcid.org/0000-0002-0129-4843"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengpeng Ji","raw_affiliation_strings":["Alibaba Tongyi Speech Lab","Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Tongyi Speech Lab","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026302891","display_name":"Qian Chen","orcid":"https://orcid.org/0000-0003-4406-5618","observed_orcids":["https://orcid.org/0000-0003-4406-5618"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Chen","raw_affiliation_strings":["Alibaba Tongyi Speech Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Tongyi Speech Lab","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396375","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0002-0356-1968","observed_orcids":["https://orcid.org/0000-0002-0356-1968"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Wang","raw_affiliation_strings":["Alibaba Tongyi Speech Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Tongyi Speech Lab","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101230918","display_name":"Jialong Zuo","orcid":"https://orcid.org/0009-0009-8548-5126","observed_orcids":["https://orcid.org/0009-0009-8548-5126","https://orcid.org/0009-0002-6876-9943"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jialong Zuo","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113394692","display_name":"Minghui Fang","orcid":"https://orcid.org/0009-0000-6488-9695","observed_orcids":["https://orcid.org/0009-0000-6488-9695"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghui Fang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083611896","display_name":"Ziyue Karen Jiang","orcid":"https://orcid.org/0009-0007-4158-4689","observed_orcids":["https://orcid.org/0009-0007-4158-4689"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyue Jiang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113241232","display_name":"Hai Shen Huang","orcid":"https://orcid.org/0009-0002-9315-1387","observed_orcids":["https://orcid.org/0009-0002-9315-1387"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hai Huang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111185441","display_name":"Z.Y. Wang","orcid":"https://orcid.org/0009-0007-6426-3749","observed_orcids":["https://orcid.org/0009-0007-6426-3749"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zehan Wang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009897266","display_name":"Xize Cheng","orcid":"https://orcid.org/0000-0001-9708-3225","observed_orcids":["https://orcid.org/0000-0001-9708-3225"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xize Cheng","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Siqi Zheng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siqi Zheng","raw_affiliation_strings":["Alibaba Tongyi Speech Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Tongyi Speech Lab","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384","observed_orcids":["https://orcid.org/0000-0001-6121-0384","https://orcid.org/0000-0002-6651-1802"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.7985,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.93854594,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6966","last_page":"6981"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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":0.9984999895095825,"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":0.0010000000474974513,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/independent-control","display_name":"independent control","score":0.3930000066757202},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"speech synthesis","score":0.4410000145435333},{"id":"https://openalex.org/keywords/text-to-speech","display_name":"text-to-speech","score":0.7350000143051147}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.7961913347244263},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.5964028239250183},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4985220432281494},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4800663888454437},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.4485357403755188},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42701494693756104},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20371854305267334},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.09172174334526062},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08026531338691711},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.07854527235031128},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.346","doi":"https://doi.org/10.18653/v1/2025.acl-long.346","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.346","pdf_url":"https://aclanthology.org/2025.acl-long.346.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2406.01205","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.01205","pdf_url":"https://arxiv.org/pdf/2406.01205","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2406.01205","doi":"https://doi.org/10.48550/arxiv.2406.01205","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.01205","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.346","doi":"https://doi.org/10.18653/v1/2025.acl-long.346","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.346","pdf_url":"https://aclanthology.org/2025.acl-long.346.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1101031052","display_name":null,"funder_award_id":"U24A20326","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6072681302","display_name":null,"funder_award_id":"62222211","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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945647.pdf","grobid_xml":"https://content.openalex.org/works/W4412945647.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415135890","https://openalex.org/W7166816086","https://openalex.org/W7119607317","https://openalex.org/W4417291460","https://openalex.org/W7084142224","https://openalex.org/W7166886664","https://openalex.org/W4385000841","https://openalex.org/W4392904245","https://openalex.org/W7117537546","https://openalex.org/W7168371421"],"abstract_inverted_index":{"In":[0],"this":[1,131],"paper,":[2],"we":[3,103,136],"present":[4],"ControlSpeech,":[5],"a":[6,53,98,139],"text-to-speech":[7],"(TTS)":[8],"system":[9,58],"capable":[10],"of":[11,23,159],"fully":[12],"cloning":[13],"the":[14,31,66,105,114],"speaker's":[15,32],"voice":[16,33,48],"and":[17,21,37,63,74,79,83,95,112,166],"enabling":[18],"arbitrary":[19],"control":[20,36,111],"adjustment":[22,38],"speaking":[24],"style.Prior":[25],"zero-shot":[26],"TTS":[27,43,57],"models":[28,44],"only":[29],"mimic":[30],"without":[34],"further":[35],"capabilities":[39],"while":[40],"prior":[41],"controllable":[42,60,142],"cannot":[45],"perform":[46],"speaker-specific":[47],"generation.Therefore,":[49],"ControlSpeech":[50,150],"focuses":[51],"on":[52,124],"more":[54],"challenging":[55],"task-a":[56],"with":[59],"timbre,":[61,93],"content,":[62,94],"style":[64,75,96,110,141],"at":[65,170],"same":[67],"time.ControlSpeech":[68],"takes":[69],"speech":[70],"prompts,":[71,73],"content":[72],"prompts":[76],"as":[77],"inputs":[78],"utilizes":[80],"bidirectional":[81],"attention":[82],"mask-based":[84],"parallel":[85],"decoding":[86],"to":[87,92,129],"capture":[88],"codec":[89,101],"representations":[90],"corresponding":[91],"in":[97,108,157],"discrete":[99],"decoupling":[100],"space.Moreover,":[102],"analyze":[104],"many-to-many":[106],"issue":[107],"textual":[109],"propose":[113],"Style":[115],"Mixture":[116],"Semantic":[117],"Density":[118],"(SMSD)":[119],"module,":[120],"which":[121],"is":[122],"based":[123],"Gaussian":[125],"mixture":[126],"density":[127],"networks,":[128],"resolve":[130],"problem.To":[132],"facilitate":[133],"empirical":[134],"validations,":[135],"make":[137],"available":[138,169],"new":[140],"dataset":[143],"called":[144],"VccmDataset.Our":[145],"experimental":[146],"results":[147],"demonstrate":[148],"that":[149],"exhibits":[151],"comparable":[152],"or":[153],"state-of-the-art":[154],"(SOTA)":[155],"performance":[156],"terms":[158],"controllability,":[160],"timbre":[161],"similarity,":[162],"audio":[163],"quality,":[164],"robustness,":[165],"generalizability.Codes":[167],"are":[168],"https://github.com/":[171],"jishengpeng/ControlSpeech.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2025-10-10T00:00:00"}
