{"id":"https://openalex.org/W4405709167","doi":"https://doi.org/10.1109/iscslp63861.2024.10800681","title":"The Codec Language Model-Based Zero-Shot Spontaneous Style TTS System for CoVoC Challenge 2024","display_name":"The Codec Language Model-Based Zero-Shot Spontaneous Style TTS System for CoVoC Challenge 2024","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709167","doi":"https://doi.org/10.1109/iscslp63861.2024.10800681"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5111291993","display_name":"Shuoyi 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/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":"Shuoyi Zhou","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University,Shenzhen"],"affiliations":[{"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/A5089348821","display_name":"Yixuan Zhou","orcid":"https://orcid.org/0000-0003-4984-2252"},"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/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":"Yixuan Zhou","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University,Shenzhen"],"affiliations":[{"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/A5064983142","display_name":"Weiyang Li","orcid":"https://orcid.org/0009-0004-8868-8723"},"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/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":"Weiqing Li.","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University,Shenzhen"],"affiliations":[{"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/A5100450139","display_name":"Jun Chen","orcid":"https://orcid.org/0000-0001-7201-1989"},"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/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":"Jun Chen","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University,Shenzhen"],"affiliations":[{"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/A5111121360","display_name":"Runchuan Ye","orcid":"https://orcid.org/0009-0001-6753-503X"},"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/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":"Runchuan Ye","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University,Shenzhen"],"affiliations":[{"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/A5113820804","display_name":"Weihao Wu","orcid":"https://orcid.org/0009-0006-4466-1080"},"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/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":"Weihao Wu","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University,Shenzhen"],"affiliations":[{"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":null,"display_name":"Zijian Lin","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/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":"Zijian Lin","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University,Shenzhen"],"affiliations":[{"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/A5087759001","display_name":"Shun Lei","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/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":"Shun Lei","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University,Shenzhen"],"affiliations":[{"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/A5111019783","display_name":"Zhiyong Wu","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/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":"Zhiyong Wu","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University,Shenzhen"],"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University,Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5111291993"],"corresponding_institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.3173,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61558062,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"496","last_page":"500"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.4742000102996826,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.4742000102996826,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.6919968128204346},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6898610591888428},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5944275856018066},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.5899389982223511},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5351245403289795},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3631904125213623},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33549243211746216},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2151191234588623},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.1293734908103943},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.09722721576690674},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07566484808921814},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.05201655626296997}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6919968128204346},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6898610591888428},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5944275856018066},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5899389982223511},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5351245403289795},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3631904125213623},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33549243211746216},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2151191234588623},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.1293734908103943},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.09722721576690674},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07566484808921814},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.05201655626296997},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W3151309757","https://openalex.org/W3198152857","https://openalex.org/W3203407300","https://openalex.org/W3209059054","https://openalex.org/W3215615641","https://openalex.org/W4283662594","https://openalex.org/W4307323391","https://openalex.org/W4390075359","https://openalex.org/W4392904093","https://openalex.org/W4400111385","https://openalex.org/W4402111455","https://openalex.org/W4402112175","https://openalex.org/W4402705930","https://openalex.org/W6748588790","https://openalex.org/W6749489859","https://openalex.org/W6784577980","https://openalex.org/W6790220310","https://openalex.org/W6838322825","https://openalex.org/W6848735303","https://openalex.org/W6850334629","https://openalex.org/W6850625674","https://openalex.org/W6853096648","https://openalex.org/W6853515095","https://openalex.org/W6854193996","https://openalex.org/W6861001475","https://openalex.org/W6861507043"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2964213236","https://openalex.org/W2163719598","https://openalex.org/W3161919736","https://openalex.org/W2387018512"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,10,41,47,81,90],"zero-shot":[4],"spontaneous":[5,31,74],"style":[6,32],"TTS":[7],"system":[8,88],"for":[9],"ISCSLP":[11],"2024":[12],"Conversational":[13],"Voice":[14],"Clone":[15],"Chal-lenge":[16],"(CoVoC).":[17],"We":[18],"propose":[19],"a":[20,26],"LLaMA-based":[21],"codec":[22],"language":[23,48],"model":[24,49,70],"with":[25,71],"delay":[27],"pattern":[28],"to":[29,50],"achieve":[30],"voice":[33],"cloning.":[34],"To":[35,57],"improve":[36],"speech":[37,75,92,100],"intelligibility,":[38],"we":[39,61],"introduce":[40],"Classifier-Free":[42],"Guidance":[43],"(CFG)":[44],"strategy":[45],"in":[46,80],"strengthen":[51],"conditional":[52],"guidance":[53],"on":[54],"token":[55],"prediction.":[56],"gen-erate":[58],"high-quality":[59,73],"utterances,":[60],"adopt":[62],"effective":[63],"data":[64],"preprocessing":[65],"operations":[66],"and":[67,97,102],"fine-tune":[68],"our":[69,87],"selected":[72],"data.":[76],"The":[77],"official":[78],"evaluations":[79],"CoVoC":[82],"constrained":[83],"track":[84],"show":[85],"that":[86],"achieves":[89],"best":[91],"naturalness":[93],"MOS":[94],"of":[95],"3.80":[96],"obtains":[98],"considerable":[99],"quality":[101],"speaker":[103],"similarity":[104],"results.":[105]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}