{"id":"https://openalex.org/W4392903006","doi":"https://doi.org/10.1109/icassp48485.2024.10448454","title":"Fewer-Token Neural Speech Codec with Time-Invariant Codes","display_name":"Fewer-Token Neural Speech Codec with Time-Invariant Codes","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903006","doi":"https://doi.org/10.1109/icassp48485.2024.10448454"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448454","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100413319","display_name":"Yong Ren","orcid":"https://orcid.org/0000-0002-6016-5582"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Ren","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,China","Institute of Automation, Chinese Academy of Sciences, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071038184","display_name":"Tao Wang","orcid":"https://orcid.org/0000-0003-1490-6973"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Wang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,China","Institute of Automation, Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078525423","display_name":"Jiangyan Yi","orcid":"https://orcid.org/0000-0003-2422-4618"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangyan Yi","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,China","Institute of Automation, Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100424047","display_name":"Le Xu","orcid":"https://orcid.org/0009-0004-3410-354X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Le Xu","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,China","School of Artificial Intelligence, University of Chinese Academy of Sciences, China","Institute of Automation, Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"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":"Jianhua Tao","raw_affiliation_strings":["Tsinghua University,Department of Automation,China","Department of Automation, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Automation, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026641664","display_name":"Chu Yuan Zhang","orcid":"https://orcid.org/0009-0006-3461-3034"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chu Yuan Zhang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,China","Institute of Automation, Chinese Academy of Sciences, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101311024","display_name":"Junzuo Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junzuo Zhou","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,China","Institute of Automation, Chinese Academy of Sciences, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12737","last_page":"12741"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9983999729156494,"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/T11309","display_name":"Music and Audio Processing","score":0.9933000206947327,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8288601040840149},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7170196175575256},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6767056584358215},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.5692475438117981},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.49225154519081116},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.46097177267074585},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4380970001220703},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.24999919533729553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8288601040840149},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7170196175575256},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6767056584358215},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.5692475438117981},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.49225154519081116},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.46097177267074585},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4380970001220703},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.24999919533729553},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448454","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1202467192","display_name":null,"funder_award_id":"U21B2010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4754633920","display_name":"\u57fa\u4e8e\u7a7a\u95f4\u91c7\u6837\u4e0e\u6df1\u5ea6\u611f\u77e5\u878d\u5408\u7b56\u7565\u7684\u8bed\u97f3\u5206\u79bb\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61971419","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G533509358","display_name":null,"funder_award_id":"62306316","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5381013183","display_name":null,"funder_award_id":"61831022","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7003438179","display_name":null,"funder_award_id":"62322120","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7270707897","display_name":null,"funder_award_id":"62206278","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7853071381","display_name":null,"funder_award_id":"62101553","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7925330915","display_name":null,"funder_award_id":"62006223","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2067295501","https://openalex.org/W2519091744","https://openalex.org/W2752796333","https://openalex.org/W2775336875","https://openalex.org/W2935711438","https://openalex.org/W2963799213","https://openalex.org/W2972359262","https://openalex.org/W2990124956","https://openalex.org/W3037038648","https://openalex.org/W3092028330","https://openalex.org/W3094002217","https://openalex.org/W3163662330","https://openalex.org/W3209059054","https://openalex.org/W3215615641","https://openalex.org/W4307323391","https://openalex.org/W4313679638","https://openalex.org/W4372279529","https://openalex.org/W4377010126","https://openalex.org/W4380551955","https://openalex.org/W4385822716","https://openalex.org/W4385823076","https://openalex.org/W4390075359","https://openalex.org/W6640212811","https://openalex.org/W6770838157","https://openalex.org/W6783867762","https://openalex.org/W6785090365","https://openalex.org/W6848735303","https://openalex.org/W6852581948","https://openalex.org/W6853188576","https://openalex.org/W6853515095"],"related_works":["https://openalex.org/W2129079178","https://openalex.org/W2060409740","https://openalex.org/W2382399415","https://openalex.org/W2374470469","https://openalex.org/W2159899134","https://openalex.org/W2787189739","https://openalex.org/W2899318368","https://openalex.org/W2352448339","https://openalex.org/W2363660481","https://openalex.org/W2129913000"],"abstract_inverted_index":{"Language":[0,55],"model":[1,56],"based":[2,57],"text-to-speech":[3],"(TTS)":[4],"models,":[5,29],"like":[6],"VALL-E,":[7],"have":[8],"gained":[9],"attention":[10],"for":[11],"their":[12],"outstanding":[13],"in-context":[14],"learning":[15],"capability":[16],"in":[17],"zero-shot":[18,131],"scenarios.":[19],"Neural":[20],"speech":[21,33,70,147,169],"codec":[22,44,71],"is":[23,176],"a":[24,67,84,112],"critical":[25],"component":[26],"of":[27,54,92,102,106,121,145,166],"these":[28],"which":[30,127],"can":[31,88,128,139],"convert":[32],"into":[34,83],"discrete":[35],"token":[36,40],"representations.":[37],"However,":[38],"excessive":[39],"sequences":[41],"from":[42],"the":[43,52,90,100,119,130,143,154,162,167,171],"may":[45],"negatively":[46],"affect":[47],"prediction":[48],"accuracy":[49],"and":[50,79,156],"restrict":[51],"progression":[53],"TTS":[58,132,172],"models.":[59],"To":[60],"address":[61],"this":[62,64,109],"issue,":[63],"paper":[65,110],"proposes":[66],"novel":[68],"neural":[69],"with":[72,148],"time-invariant":[73,81,113,122],"codes":[74,105],"named":[75],"TiCodec.":[76],"By":[77],"encoding":[78,114],"quantizing":[80],"information":[82,94],"separate":[85],"code,":[86],"TiCodec":[87,138],"reduce":[89,161],"amount":[91],"frame-level":[93],"that":[95,137],"needs":[96],"encoding,":[97],"effectively":[98],"decreasing":[99],"number":[101],"tokens":[103,150],"as":[104,158,160],"speech.":[107],"Furthermore,":[108],"introduces":[111],"consistency":[115,120],"loss":[116],"to":[117],"enhance":[118,142],"code":[123,175],"within":[124],"an":[125],"utterance,":[126],"benefit":[129],"task.":[133],"Experimental":[134],"results":[135],"demonstrate":[136],"not":[140],"only":[141],"quality":[144],"reconstruction":[146],"fewer":[149],"but":[151],"also":[152],"increase":[153],"similarity":[155],"naturalness,":[157],"well":[159],"word":[163],"error":[164],"rate":[165],"synthesized":[168],"by":[170],"model.":[173],"The":[174],"publicly":[177],"available":[178],"at":[179],"https://github.com/y-ren16/TiCodec.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}