{"id":"https://openalex.org/W4417305271","doi":"https://doi.org/10.1109/tpami.2025.3643619","title":"Recent Advances in Discrete Speech Tokens: A Review","display_name":"Recent Advances in Discrete Speech Tokens: A Review","publication_year":2025,"publication_date":"2025-12-12","ids":{"openalex":"https://openalex.org/W4417305271","doi":"https://doi.org/10.1109/tpami.2025.3643619","pmid":"https://pubmed.ncbi.nlm.nih.gov/41385436"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3643619","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3643619","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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":false,"raw_author_name":"Yiwei Guo","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing; X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-8114-2085","affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing; X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100605168","display_name":"Zhihan Li","orcid":"https://orcid.org/0000-0002-6290-6575"},"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":"Zhihan Li","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing; X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing; X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hankun Wang","orcid":"https://orcid.org/0009-0008-7959-0336"},"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":["MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing; X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-7959-0336","affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing; X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443980","display_name":"Bohan Li","orcid":"https://orcid.org/0000-0003-1909-8995"},"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":"Bohan Li","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing; X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing; X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chongtian Shao","orcid":"https://orcid.org/0009-0000-1157-4032"},"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":"Chongtian Shao","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing; X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-1157-4032","affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing; X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109652724","display_name":"Hanglei Zhang","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":"Hanglei Zhang","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing; X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-7130-0500","affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing; X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","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":["MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing; X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5329-0847","affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing; X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101070252","display_name":"Chen Xie","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":"Xie Chen","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing; X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7423-617X","affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing; X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101635405","display_name":"Shujie Liu","orcid":"https://orcid.org/0009-0008-2599-6752"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shujie Liu","raw_affiliation_strings":["Microsoft Research Asia (MSRA), Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-2599-6752","affiliations":[{"raw_affiliation_string":"Microsoft Research Asia (MSRA), Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111980517","display_name":"Kai Yu","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":"Kai Yu","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing; X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7102-9826","affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing; X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":16.7519,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.9905315,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"48","issue":"4","first_page":"4184","last_page":"4204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8183000087738037,"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":0.8183000087738037,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.033799998462200165,"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":0.02539999969303608,"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/security-token","display_name":"Security token","score":0.5358999967575073},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5149000287055969},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4925000071525574},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4821999967098236},{"id":"https://openalex.org/keywords/principal","display_name":"Principal (computer security)","score":0.4641999900341034},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.3792000114917755},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3716000020503998}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.800000011920929},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5358999967575073},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5149000287055969},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4925000071525574},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4821999967098236},{"id":"https://openalex.org/C144559511","wikidata":"https://www.wikidata.org/wiki/Q2986279","display_name":"Principal (computer security)","level":2,"score":0.4641999900341034},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3846000134944916},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.3792000114917755},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3716000020503998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37130001187324524},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34540000557899475},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.2793000042438507},{"id":"https://openalex.org/C2778464652","wikidata":"https://www.wikidata.org/wiki/Q309849","display_name":"Open research","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3643619","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3643619","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41385436","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41385436","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":132,"referenced_works":["https://openalex.org/W1481955708","https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1700083040","https://openalex.org/W1747414053","https://openalex.org/W1886421314","https://openalex.org/W2124509324","https://openalex.org/W2133665775","https://openalex.org/W2141998673","https://openalex.org/W2972359262","https://openalex.org/W2972867623","https://openalex.org/W2973049979","https://openalex.org/W3049256661","https://openalex.org/W3089425003","https://openalex.org/W3093096176","https://openalex.org/W3095361818","https://openalex.org/W3097777922","https://openalex.org/W3097787369","https://openalex.org/W3100460087","https://openalex.org/W3140429000","https://openalex.org/W3175871055","https://openalex.org/W3180355996","https://openalex.org/W3197273793","https://openalex.org/W3197580070","https://openalex.org/W3198217962","https://openalex.org/W3198429080","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3210177631","https://openalex.org/W3213029956","https://openalex.org/W3215615641","https://openalex.org/W4221159457","https://openalex.org/W4225635674","https://openalex.org/W4226132755","https://openalex.org/W4226162428","https://openalex.org/W4226507725","https://openalex.org/W4244017338","https://openalex.org/W4252812408","https://openalex.org/W4281492411","https://openalex.org/W4284888249","https://openalex.org/W4292825791","https://openalex.org/W4297841405","https://openalex.org/W4310494058","https://openalex.org/W4313021454","https://openalex.org/W4319862416","https://openalex.org/W4372259964","https://openalex.org/W4372270198","https://openalex.org/W4375868953","https://openalex.org/W4375869380","https://openalex.org/W4377231659","https://openalex.org/W4381786045","https://openalex.org/W4385245566","https://openalex.org/W4385570101","https://openalex.org/W4385571911","https://openalex.org/W4385814073","https://openalex.org/W4385822683","https://openalex.org/W4385822740","https://openalex.org/W4385823003","https://openalex.org/W4385823130","https://openalex.org/W4386752790","https://openalex.org/W4390075359","https://openalex.org/W4392902857","https://openalex.org/W4392903006","https://openalex.org/W4392903089","https://openalex.org/W4392903159","https://openalex.org/W4392903389","https://openalex.org/W4392904409","https://openalex.org/W4392909068","https://openalex.org/W4392909760","https://openalex.org/W4392931975","https://openalex.org/W4393147067","https://openalex.org/W4399875170","https://openalex.org/W4400111385","https://openalex.org/W4401070302","https://openalex.org/W4402111239","https://openalex.org/W4402111456","https://openalex.org/W4402111497","https://openalex.org/W4402111612","https://openalex.org/W4402111715","https://openalex.org/W4402111780","https://openalex.org/W4402111799","https://openalex.org/W4402112198","https://openalex.org/W4402112366","https://openalex.org/W4402112381","https://openalex.org/W4402112436","https://openalex.org/W4402112533","https://openalex.org/W4402116599","https://openalex.org/W4402669711","https://openalex.org/W4402670057","https://openalex.org/W4402672020","https://openalex.org/W4402672068","https://openalex.org/W4402915905","https://openalex.org/W4404740148","https://openalex.org/W4404782459","https://openalex.org/W4404782909","https://openalex.org/W4405709614","https://openalex.org/W4405974781","https://openalex.org/W4406417959","https://openalex.org/W4406461300","https://openalex.org/W4406461319","https://openalex.org/W4406461437","https://openalex.org/W4406461625","https://openalex.org/W4406461749","https://openalex.org/W4406495593","https://openalex.org/W4406858439","https://openalex.org/W4408017609","https://openalex.org/W4408351812","https://openalex.org/W4408351949","https://openalex.org/W4408352880","https://openalex.org/W4408353320","https://openalex.org/W4408353629","https://openalex.org/W4408353695","https://openalex.org/W4408354466","https://openalex.org/W4408355053","https://openalex.org/W4408355207","https://openalex.org/W4409362462","https://openalex.org/W4409362648","https://openalex.org/W4411119792","https://openalex.org/W4411232650","https://openalex.org/W4412886819","https://openalex.org/W4412944867","https://openalex.org/W4412945298","https://openalex.org/W4412945617","https://openalex.org/W4413472064","https://openalex.org/W4415433232","https://openalex.org/W4415433281","https://openalex.org/W4415433294","https://openalex.org/W4415433412","https://openalex.org/W4415433503","https://openalex.org/W4415433959","https://openalex.org/W4416037241","https://openalex.org/W7133219565"],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"advancement":[2],"of":[3,10,58,80,115,120,158],"speech":[4,18,25,59,68,109,160],"generation":[5],"technologies":[6],"in":[7,107,136,153],"the":[8,51,101,116,137,154],"era":[9],"large":[11],"language":[12,52],"models":[13],"(LLMs)":[14],"has":[15,82],"established":[16],"discrete":[17,67,108,159],"tokens":[19,69,75],"as":[20],"a":[21,85,112],"foundational":[22],"paradigm":[23],"for":[24,41],"representation.":[26],"These":[27],"tokens,":[28,78],"characterized":[29,89],"by":[30,90],"their":[31],"discrete,":[32],"compact,":[33],"and":[34,44,76,94,104,118,123,139,156],"concise":[35],"nature,":[36],"are":[37],"not":[38],"only":[39],"advantageous":[40],"efficient":[42],"transmission":[43],"storage,":[45],"but":[46],"also":[47],"inherently":[48],"compatible":[49],"with":[50],"modeling":[53],"framework,":[54],"enabling":[55],"seamless":[56],"integration":[57],"into":[60,70,84],"text-dominated":[61],"LLM":[62],"architectures.":[63],"Current":[64],"research":[65,87,142],"categorizes":[66],"two":[71],"principal":[72],"classes:":[73],"acoustic":[74],"semantic":[77],"each":[79,121],"which":[81],"evolved":[83],"rich":[86],"domain":[88],"unique":[91],"design":[92],"philosophies":[93],"methodological":[95],"approaches.":[96],"This":[97],"survey":[98],"systematically":[99],"synthesizes":[100],"existing":[102],"taxonomy":[103],"recent":[105],"innovations":[106],"tokenization,":[110],"conducts":[111],"critical":[113],"examination":[114],"strengths":[117],"limitations":[119],"paradigm,":[122],"presents":[124],"systematic":[125],"experimental":[126],"comparisons":[127],"across":[128],"token":[129],"types.":[130],"Furthermore,":[131],"we":[132],"identify":[133],"persistent":[134],"challenges":[135],"field":[138],"propose":[140],"potential":[141],"directions,":[143],"aiming":[144],"to":[145,149],"offer":[146],"actionable":[147],"insights":[148],"inspire":[150],"future":[151],"advancements":[152],"development":[155],"application":[157],"tokens.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-12T00:00:00"}