{"id":"https://openalex.org/W4406461271","doi":"https://doi.org/10.1109/slt61566.2024.10832255","title":"Amphion: an Open-Source Audio, Music, and Speech Generation Toolkit","display_name":"Amphion: an Open-Source Audio, Music, and Speech Generation Toolkit","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461271","doi":"https://doi.org/10.1109/slt61566.2024.10832255"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832255","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832255","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5100617728","display_name":"Xueyao Zhang","orcid":"https://orcid.org/0000-0003-3135-551X"},"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":true,"raw_author_name":"Xueyao Zhang","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]}]},{"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":["The Chinese University of Hong Kong,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102714342","display_name":"Yicheng Gu","orcid":"https://orcid.org/0000-0002-0506-3364"},"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":"Yicheng Gu","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090055283","display_name":"Yuancheng Wang","orcid":"https://orcid.org/0000-0002-6253-8311"},"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":"Yuancheng Wang","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100325954","display_name":"Jiaqi Li","orcid":"https://orcid.org/0000-0002-8330-0230"},"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":"Jiaqi Li","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033905098","display_name":"Haorui He","orcid":null},"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":"Haorui He","raw_affiliation_strings":["Shenzhen Reseach Institute of Big Data,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Reseach Institute of Big Data,Shenzhen,China","institution_ids":["https://openalex.org/I4210099586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005342759","display_name":"Chaoren Wang","orcid":null},"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":"Chaoren Wang","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045623329","display_name":"Songting Liu","orcid":null},"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":"Songting Liu","raw_affiliation_strings":["Shenzhen Reseach Institute of Big Data,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Reseach Institute of Big Data,Shenzhen,China","institution_ids":["https://openalex.org/I4210099586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100718286","display_name":"Xi Chen","orcid":"https://orcid.org/0000-0003-2254-460X"},"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":"Xi Chen","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013313233","display_name":"J. S. Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junan Zhang","raw_affiliation_strings":["Shanghai AI Laboratory,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory,Shanghai,China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109797442","display_name":"Zihao Fang","orcid":null},"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":"Zihao Fang","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080204035","display_name":"Haopeng Chen","orcid":"https://orcid.org/0000-0002-4535-5038"},"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":"Haopeng Chen","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108965091","display_name":"Tianze Tang","orcid":null},"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":"Tze Ying Tang","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101257950","display_name":"Lexiao Zou","orcid":null},"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":"Lexiao Zou","raw_affiliation_strings":["Shenzhen Reseach Institute of Big Data,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Reseach Institute of Big Data,Shenzhen,China","institution_ids":["https://openalex.org/I4210099586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043256966","display_name":"Mingxuan Wang","orcid":"https://orcid.org/0000-0002-2858-6512"},"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":"Mingxuan Wang","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100820799","display_name":"Jun Han","orcid":null},"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":"Jun Han","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437976","display_name":"Kai Chen","orcid":"https://orcid.org/0000-0002-5624-2987"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Chen","raw_affiliation_strings":["Shanghai AI Laboratory,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory,Shanghai,China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"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":"Haizhou Li","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102765381","display_name":"Zhizheng Wu","orcid":"https://orcid.org/0009-0001-1192-9857"},"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":"Zhizheng Wu","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":19,"corresponding_author_ids":["https://openalex.org/A5100617728"],"corresponding_institution_ids":["https://openalex.org/I4210116924"],"apc_list":null,"apc_paid":null,"fwci":6.2194,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.97413473,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"879","last_page":"884"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9991000294685364,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.7722632884979248},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.6210806965827942},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5084902048110962},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07206487655639648},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.06854066252708435}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7722632884979248},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.6210806965827942},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5084902048110962},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07206487655639648},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.06854066252708435}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832255","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832255","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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":47,"referenced_works":["https://openalex.org/W2519091744","https://openalex.org/W2963300588","https://openalex.org/W2970006822","https://openalex.org/W2972359262","https://openalex.org/W2995181338","https://openalex.org/W3033411150","https://openalex.org/W3094550259","https://openalex.org/W3095410713","https://openalex.org/W3096159803","https://openalex.org/W3103104054","https://openalex.org/W3129651364","https://openalex.org/W3169905056","https://openalex.org/W3198020407","https://openalex.org/W3209059054","https://openalex.org/W4281736089","https://openalex.org/W4285345683","https://openalex.org/W4296068763","https://openalex.org/W4298580827","https://openalex.org/W4307323391","https://openalex.org/W4313679638","https://openalex.org/W4318752004","https://openalex.org/W4362598673","https://openalex.org/W4366460484","https://openalex.org/W4367359628","https://openalex.org/W4372262501","https://openalex.org/W4377000449","https://openalex.org/W4392538788","https://openalex.org/W4392909842","https://openalex.org/W4400376071","https://openalex.org/W4400480473","https://openalex.org/W4402044753","https://openalex.org/W4402830263","https://openalex.org/W4405709542","https://openalex.org/W4406462037","https://openalex.org/W6748409065","https://openalex.org/W6767111847","https://openalex.org/W6778823374","https://openalex.org/W6783182287","https://openalex.org/W6785954764","https://openalex.org/W6796464841","https://openalex.org/W6838843145","https://openalex.org/W6848735303","https://openalex.org/W6849109464","https://openalex.org/W6851290578","https://openalex.org/W6851724922","https://openalex.org/W6862144568","https://openalex.org/W6870299770"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Amphion":[0,74,115],"is":[1,49,116],"an":[2],"open-source":[3],"toolkit":[4,48],"for":[5,16,44],"Audio,":[6],"Music,":[7],"and":[8,19,34,54,60,90,104],"Speech":[9,84],"Generation,":[10],"targeting":[11],"to":[12,63,83,87],"ease":[13],"the":[14,37],"way":[15],"junior":[17],"researchers":[18,62],"engineers":[20],"into":[21],"these":[22],"fields.":[23],"It":[24],"presents":[25,109],"a":[26,77,110],"unified":[27],"framework":[28],"that":[29],"includes":[30],"diverse":[31],"generation":[32],"tasks":[33,80],"models,":[35,56],"with":[36,51,67],"added":[38],"bonus":[39],"of":[40,73,79,113],"being":[41],"easily":[42],"extendable":[43],"new":[45],"incorporation.":[46],"The":[47,70],"designed":[50],"beginner-friendly":[52],"workflows":[53],"pre-trained":[55],"allowing":[57],"both":[58],"beginners":[59],"seasoned":[61],"kick-start":[64],"their":[65],"projects":[66],"relative":[68],"ease.":[69],"initial":[71],"release":[72],"v0.1":[75],"supports":[76],"range":[78],"including":[81],"Text":[82,86],"(TTS),":[85],"Audio":[88],"(TTA),":[89],"Singing":[91],"Voice":[92],"Conversion":[93],"(SVC),":[94],"supplemented":[95],"by":[96],"essential":[97],"components":[98],"like":[99],"data":[100],"preprocessing,":[101],"state-of-the-art":[102],"vocoders,":[103],"evaluation":[105],"metrics.":[106],"This":[107],"paper":[108],"high-level":[111],"overview":[112],"Amphion.":[114],"open-sourced":[117],"at":[118],"https://github.com/open-mmlab/Amphion.":[119]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":4}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}