{"id":"https://openalex.org/W4405709385","doi":"https://doi.org/10.1109/iscslp63861.2024.10800694","title":"The ISCSLP 2024 Conversational Voice Clone (CoVoC) Challenge: Tasks, Results and Findings","display_name":"The ISCSLP 2024 Conversational Voice Clone (CoVoC) Challenge: Tasks, Results and Findings","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709385","doi":"https://doi.org/10.1109/iscslp63861.2024.10800694"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800694","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800694","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/A5114634719","display_name":"Kangxiang Xia","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":true,"raw_author_name":"Kangxiang Xia","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi&#x0027;an"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi&#x0027;an","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101377824","display_name":"Dake Guo","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":"Dake Guo","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi&#x0027;an"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi&#x0027;an","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015560758","display_name":"Jixun Yao","orcid":"https://orcid.org/0000-0002-5324-7360"},"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":"Jixun Yao","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi&#x0027;an"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi&#x0027;an","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009337933","display_name":"Liumeng Xue","orcid":"https://orcid.org/0000-0003-2815-8494"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liumeng Xue","raw_affiliation_strings":["School of Data Science, The Chinese University of Hong Kong,Shenzhen"],"affiliations":[{"raw_affiliation_string":"School of Data Science, The Chinese University of Hong Kong,Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016567570","display_name":"Hanzhao Li","orcid":"https://orcid.org/0009-0005-3215-7517"},"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":"Hanzhao Li","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi&#x0027;an"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi&#x0027;an","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328371","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0002-5073-3371"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["Shenzhen Research Institute of Big Data (SRIBD)"],"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data (SRIBD)","institution_ids":["https://openalex.org/I4210099586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100683933","display_name":"Zhao Guo","orcid":"https://orcid.org/0000-0003-1477-0842"},"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":"Zhao Guo","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi&#x0027;an"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi&#x0027;an","institution_ids":["https://openalex.org/I17145004"]}]},{"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":["School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi&#x0027;an"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi&#x0027;an","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375554","display_name":"Qingqing Zhang","orcid":"https://orcid.org/0009-0007-9373-3527"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingqing Zhang","raw_affiliation_strings":["Magic data"],"affiliations":[{"raw_affiliation_string":"Magic data","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102840095","display_name":"Lei Luo","orcid":"https://orcid.org/0000-0001-8620-6410"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Luo","raw_affiliation_strings":["Magic data"],"affiliations":[{"raw_affiliation_string":"Magic data","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618884","display_name":"Minghui Dong","orcid":"https://orcid.org/0000-0002-6965-2862"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Minghui Dong","raw_affiliation_strings":["Insitutue for Infocomm Research (I2R)"],"affiliations":[{"raw_affiliation_string":"Insitutue for Infocomm Research (I2R)","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028986731","display_name":"Peng Sun","orcid":"https://orcid.org/0000-0002-4782-0693"},"institutions":[{"id":"https://openalex.org/I4210100924","display_name":"China Computer Federation","ror":"https://ror.org/015xj5w40","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Sun","raw_affiliation_strings":["China Computer Federation"],"affiliations":[{"raw_affiliation_string":"China Computer Federation","institution_ids":["https://openalex.org/I4210100924"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5114634719"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.7274,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.78085142,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"506","last_page":"510"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12128","display_name":"AI in Service Interactions","score":0.9337000250816345,"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/T12128","display_name":"AI in Service Interactions","score":0.9337000250816345,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6990360021591187},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.607170581817627},{"id":"https://openalex.org/keywords/clone","display_name":"clone (Java method)","score":0.5883358120918274},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.42001521587371826},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4037785232067108},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1775434911251068},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.05984112620353699},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.04860043525695801}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6990360021591187},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.607170581817627},{"id":"https://openalex.org/C81089528","wikidata":"https://www.wikidata.org/wiki/Q5134986","display_name":"clone (Java method)","level":3,"score":0.5883358120918274},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.42001521587371826},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4037785232067108},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1775434911251068},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.05984112620353699},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.04860043525695801},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800694","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800694","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2962788625","https://openalex.org/W2963609956","https://openalex.org/W3198152857","https://openalex.org/W3203407300","https://openalex.org/W4283067311","https://openalex.org/W4307323391","https://openalex.org/W4372346850","https://openalex.org/W4387595589","https://openalex.org/W4390075359","https://openalex.org/W4390872297","https://openalex.org/W4392904093","https://openalex.org/W4395957972","https://openalex.org/W4402111239","https://openalex.org/W4402111455","https://openalex.org/W4402112175","https://openalex.org/W6763832098","https://openalex.org/W6796464841","https://openalex.org/W6846539466","https://openalex.org/W6848735303","https://openalex.org/W6852421699","https://openalex.org/W6852870047","https://openalex.org/W6853096648"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2377327490","https://openalex.org/W2560253012","https://openalex.org/W1524590520","https://openalex.org/W2742181818","https://openalex.org/W2612412344","https://openalex.org/W2053633997","https://openalex.org/W337810568"],"abstract_inverted_index":{"The":[0,27,79],"ISCSLP":[1],"2024":[2],"Conversational":[3],"Voice":[4],"Clone":[5],"(CoVoC)":[6],"Challenge":[7],"aims":[8],"to":[9],"benchmark":[10],"and":[11,39,42,77],"advance":[12],"zero-shot":[13],"spontaneous":[14,22],"style":[15],"voice":[16],"cloning,":[17],"particularly":[18],"focusing":[19],"on":[20,37],"generating":[21],"behaviors":[23],"in":[24],"conversational":[25,57],"speech.":[26],"challenge":[28],"comprises":[29],"two":[30],"tracks:":[31],"an":[32],"unconstrained":[33],"track":[34,45],"without":[35],"limitation":[36],"data":[38],"model":[40],"usage,":[41],"a":[43],"constrained":[44,51],"only":[46],"allowing":[47],"the":[48,65,70],"use":[49],"of":[50],"open-source":[52],"datasets.":[53],"A":[54],"100-hour":[55],"high-quality":[56],"speech":[58],"dataset":[59],"is":[60,83],"also":[61],"made":[62],"available":[63],"with":[64],"challenge.":[66],"This":[67],"paper":[68],"details":[69],"data,":[71],"tracks,":[72],"submitted":[73],"systems,":[74],"evaluation":[75],"results,":[76],"findings.":[78],"challenge's":[80],"official":[81],"website":[82],"https://www.magicdatatech.com/iscslp-2024.":[84]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
