{"id":"https://openalex.org/W4405709384","doi":"https://doi.org/10.1109/iscslp63861.2024.10800009","title":"The X-Lance Technical Report for Interspeech 2024 Speech Processing using Discrete Speech Unit Challenge","display_name":"The X-Lance Technical Report for Interspeech 2024 Speech Processing using Discrete Speech Unit Challenge","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709384","doi":"https://doi.org/10.1109/iscslp63861.2024.10800009"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800009","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/A5101579214","display_name":"Yiwei Guo","orcid":"https://orcid.org/0009-0003-8114-2085"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiwei Guo","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113177016","display_name":"Chenrun Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenrun Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101407134","display_name":"Yifan Yang","orcid":"https://orcid.org/0000-0003-4491-3728"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Yang","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103183873","display_name":"Hankun Wang","orcid":"https://orcid.org/0000-0003-0338-1809"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hankun Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438492","display_name":"Ziyang Ma","orcid":"https://orcid.org/0000-0002-0623-9114"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Ma","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035532752","display_name":"Chenpeng Du","orcid":"https://orcid.org/0000-0001-5329-0847"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenpeng Du","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328340","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0003-1523-9631"},"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"],"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data","institution_ids":["https://openalex.org/I4210099586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067766584","display_name":"H. B. Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hanzheng Li","raw_affiliation_strings":["AISpeech Ltd"],"affiliations":[{"raw_affiliation_string":"AISpeech Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100766936","display_name":"Xu Li","orcid":"https://orcid.org/0000-0001-6619-0562"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu Li","raw_affiliation_strings":["AISpeech Ltd"],"affiliations":[{"raw_affiliation_string":"AISpeech Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101852911","display_name":"Shuai Fan","orcid":"https://orcid.org/0000-0001-7364-7815"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuai Fan","raw_affiliation_strings":["AISpeech Ltd"],"affiliations":[{"raw_affiliation_string":"AISpeech Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092171914","display_name":"Hui Zhang","orcid":"https://orcid.org/0009-0009-2257-333X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hui Zhang","raw_affiliation_strings":["AISpeech Ltd"],"affiliations":[{"raw_affiliation_string":"AISpeech Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101293966","display_name":"Xie Chen","orcid":"https://orcid.org/0009-0004-4458-0753"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":13,"corresponding_author_ids":["https://openalex.org/A5101579214"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2126728,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"641","last_page":"645"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9190999865531921,"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":0.9190999865531921,"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":0.7825967073440552},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7175838947296143},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.6026822328567505},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.5291041731834412},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.43479830026626587},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4209236204624176},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3730890154838562},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.05800178647041321},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.050251305103302}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7825967073440552},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7175838947296143},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.6026822328567505},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.5291041731834412},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.43479830026626587},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4209236204624176},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3730890154838562},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.05800178647041321},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.050251305103302}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800009","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":32,"referenced_works":["https://openalex.org/W2143612262","https://openalex.org/W2972359262","https://openalex.org/W2995181338","https://openalex.org/W3015686596","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3215615641","https://openalex.org/W4225956675","https://openalex.org/W4226132755","https://openalex.org/W4283700324","https://openalex.org/W4296068763","https://openalex.org/W4307323391","https://openalex.org/W4381786045","https://openalex.org/W4390075359","https://openalex.org/W4392903389","https://openalex.org/W4392909760","https://openalex.org/W4393147067","https://openalex.org/W6629717138","https://openalex.org/W6631362777","https://openalex.org/W6638575559","https://openalex.org/W6769196770","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6800393981","https://openalex.org/W6847363464","https://openalex.org/W6848735303","https://openalex.org/W6853004994","https://openalex.org/W6853515095","https://openalex.org/W6853771913","https://openalex.org/W6857062747","https://openalex.org/W6857478255","https://openalex.org/W6861001475"],"related_works":["https://openalex.org/W1911859126","https://openalex.org/W1546240199","https://openalex.org/W2120730869","https://openalex.org/W1569721167","https://openalex.org/W193702574","https://openalex.org/W2541680182","https://openalex.org/W2166699153","https://openalex.org/W2063862874","https://openalex.org/W2164147372","https://openalex.org/W2053531689"],"abstract_inverted_index":{"Discrete":[0,56],"speech":[1,11,16],"tokens":[2],"have":[3],"been":[4],"more":[5,7],"and":[6,21,46,82,92],"popular":[8],"in":[9,49,72],"multiple":[10],"processing":[12],"fields,":[13],"including":[14],"automatic":[15],"recognition":[17],"(ASR),":[18],"text-to-speech":[19],"(TTS)":[20],"singing":[22],"voice":[23],"syn-thesis":[24],"(SVS).":[25],"In":[26],"this":[27],"paper,":[28],"we":[29,61],"describe":[30],"the":[31,35,40,50,66,73,78,88],"systems":[32],"developed":[33],"by":[34],"SJTU":[36],"X-LANCE":[37],"group":[38],"for":[39],"TTS":[41,74],"(acoustic":[42],"+":[43],"vocoder),":[44],"SVS,":[45],"ASR":[47],"tracks":[48],"Interspeech":[51],"2024":[52],"Speech":[53,57],"Processing":[54],"Using":[55],"Unit":[58],"Challenge.":[59],"Notably,":[60],"achieved":[62],"1st":[63],"rank":[64],"on":[65],"leaderboard<sup":[67],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[68,70],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup><sup":[69],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>https://huggingface.co/spaces/discrete-speech/interspeech2024_discrete_speech_tts_full":[71],"track":[75],"both":[76],"with":[77,87],"whole":[79],"training":[80,85],"set":[81],"only":[83],"1h":[84],"data,":[86],"highest":[89],"UTMOS":[90],"score":[91],"lowest":[93],"bitrate":[94],"among":[95],"all":[96],"submissions.":[97]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
