{"id":"https://openalex.org/W4417002762","doi":"https://doi.org/10.1109/jstsp.2025.3640535","title":"A Survey on Speech Large Language Models for Understanding","display_name":"A Survey on Speech Large Language Models for Understanding","publication_year":2025,"publication_date":"2025-12-04","ids":{"openalex":"https://openalex.org/W4417002762","doi":"https://doi.org/10.1109/jstsp.2025.3640535"},"language":null,"primary_location":{"id":"doi:10.1109/jstsp.2025.3640535","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2025.3640535","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Journal of Selected Topics in Signal Processing","raw_type":"journal-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/A5115588630","display_name":"Jing Peng","orcid":"https://orcid.org/0009-0002-0858-1527"},"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":"Jing Peng","raw_affiliation_strings":["X-LANCE Lab, School of Computer Science, MoE Key Laboratory of Artificial Intelligence, Jiangsu Key Laboratory of Language Computing, Shanghai Jiao Tong University, Shanghai, China","X-LANCE Lab, School of Computer Science, MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-0858-1527","affiliations":[{"raw_affiliation_string":"X-LANCE Lab, School of Computer Science, MoE Key Laboratory of Artificial Intelligence, Jiangsu Key Laboratory of Language Computing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"X-LANCE Lab, School of Computer Science, MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yucheng Wang","orcid":"https://orcid.org/0000-0002-7039-9235"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yucheng Wang","raw_affiliation_strings":["ETH Z&#x00FC;rich, Z&#x00FC;rich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-7039-9235","affiliations":[{"raw_affiliation_string":"ETH Z&#x00FC;rich, Z&#x00FC;rich, Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bohan Li","orcid":"https://orcid.org/0009-0004-4428-4065"},"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":["X-LANCE Lab, School of Computer Science, MoE Key Laboratory of Artificial Intelligence, Jiangsu Key Laboratory of Language Computing, Shanghai Jiao Tong University, Shanghai, China","X-LANCE Lab, School of Computer Science, MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-4428-4065","affiliations":[{"raw_affiliation_string":"X-LANCE Lab, School of Computer Science, MoE Key Laboratory of Artificial Intelligence, Jiangsu Key Laboratory of Language Computing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"X-LANCE Lab, School of Computer Science, MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","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":["X-LANCE Lab, School of Computer Science, MoE Key Laboratory of Artificial Intelligence, Jiangsu Key Laboratory of Language Computing, Shanghai Jiao Tong University, Shanghai, China","X-LANCE Lab, School of Computer Science, MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-8114-2085","affiliations":[{"raw_affiliation_string":"X-LANCE Lab, School of Computer Science, MoE Key Laboratory of Artificial Intelligence, Jiangsu Key Laboratory of Language Computing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"X-LANCE Lab, School of Computer Science, MoE Key Lab of Artificial Intelligence 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":["X-LANCE Lab, School of Computer Science, MoE Key Laboratory of Artificial Intelligence, Jiangsu Key Laboratory of Language Computing, Shanghai Jiao Tong University, Shanghai, China","X-LANCE Lab, School of Computer Science, MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-7959-0336","affiliations":[{"raw_affiliation_string":"X-LANCE Lab, School of Computer Science, MoE Key Laboratory of Artificial Intelligence, Jiangsu Key Laboratory of Language Computing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"X-LANCE Lab, School of Computer Science, MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"YanGui Fang","orcid":"https://orcid.org/0009-0002-7677-4697"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"YanGui Fang","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0002-7677-4697","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112125021","display_name":"Yu Xi","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":"Yu Xi","raw_affiliation_strings":["X-LANCE Lab, School of Computer Science, MoE Key Laboratory of Artificial Intelligence, Jiangsu Key Laboratory of Language Computing, Shanghai Jiao Tong University, Shanghai, China","X-LANCE Lab, School of Computer Science, MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-8448-0190","affiliations":[{"raw_affiliation_string":"X-LANCE Lab, School of Computer Science, MoE Key Laboratory of Artificial Intelligence, Jiangsu Key Laboratory of Language Computing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"X-LANCE Lab, School of Computer Science, MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078072988","display_name":"Haoyu Li","orcid":"https://orcid.org/0009-0001-8096-4664"},"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":"Haoyu Li","raw_affiliation_strings":["X-LANCE Lab, School of Computer Science, MoE Key Laboratory of Artificial Intelligence, Jiangsu Key Laboratory of Language Computing, Shanghai Jiao Tong University, Shanghai, China","X-LANCE Lab, School of Computer Science, MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-8096-4664","affiliations":[{"raw_affiliation_string":"X-LANCE Lab, School of Computer Science, MoE Key Laboratory of Artificial Intelligence, Jiangsu Key Laboratory of Language Computing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"X-LANCE Lab, School of Computer Science, MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xu Li","orcid":"https://orcid.org/0009-0000-8239-8320"},"institutions":[{"id":"https://openalex.org/I3132008252","display_name":"Nanjing Foreign Language School","ror":"https://ror.org/03wvwbe92","country_code":"CN","type":"education","lineage":["https://openalex.org/I3132008252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Li","raw_affiliation_strings":["AISpeech Company, Ltd., Jiangsu Key Laboratory of Language Computing, Suzhou, China","AISpeech Co., Ltd., Suzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-8239-8320","affiliations":[{"raw_affiliation_string":"AISpeech Company, Ltd., Jiangsu Key Laboratory of Language Computing, Suzhou, China","institution_ids":["https://openalex.org/I3132008252"]},{"raw_affiliation_string":"AISpeech Co., Ltd., Suzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100643115","display_name":"Ke Zhang","orcid":"https://orcid.org/0000-0002-2536-6426"},"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":"Ke Zhang","raw_affiliation_strings":["School of Data Science, The Chinese University of Hong Kong, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"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/I308837","display_name":"Suzhou University of Science and Technology","ror":"https://ror.org/04en8wb91","country_code":"CN","type":"education","lineage":["https://openalex.org/I308837"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["School of Intelligence Science and Technology, Nanjing University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1523-9631","affiliations":[{"raw_affiliation_string":"School of Intelligence Science and Technology, Nanjing University, Suzhou, China","institution_ids":["https://openalex.org/I308837","https://openalex.org/I881766915"]}]},{"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":["X-LANCE Lab, School of Computer Science, MoE Key Laboratory of Artificial Intelligence, Jiangsu Key Laboratory of Language Computing, Shanghai Jiao Tong University, Shanghai, China","X-LANCE Lab, School of Computer Science, MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7102-9826","affiliations":[{"raw_affiliation_string":"X-LANCE Lab, School of Computer Science, MoE Key Laboratory of Artificial Intelligence, Jiangsu Key Laboratory of Language Computing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"X-LANCE Lab, School of Computer Science, MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2501,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.95720778,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"20","issue":"1","first_page":"2","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.3165000081062317,"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":0.3165000081062317,"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/T12031","display_name":"Speech and dialogue systems","score":0.2160000056028366,"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":0.08060000091791153,"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/scope","display_name":"Scope (computer science)","score":0.585099995136261},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4787999987602234},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4749000072479248},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.4465000033378601},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.41679999232292175},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.40230000019073486},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.3718000054359436},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.36559998989105225},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.3472999930381775}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8277999758720398},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.585099995136261},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5126000046730042},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4787999987602234},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4749000072479248},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4465000033378601},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41679999232292175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4156000018119812},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.40230000019073486},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3718000054359436},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.36559998989105225},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.3422999978065491},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.33719998598098755},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C70587473","wikidata":"https://www.wikidata.org/wiki/Q7834111","display_name":"Transformative learning","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.30140000581741333},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.2752000093460083},{"id":"https://openalex.org/C189708586","wikidata":"https://www.wikidata.org/wiki/Q1504425","display_name":"Systematic review","level":3,"score":0.2554999887943268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2025.3640535","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2025.3640535","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Speech":[0,41,100,149,188],"understanding":[1,55,75],"is":[2],"essential":[3],"for":[4,24,160,177],"interpreting":[5],"the":[6,38,71,133],"diverse":[7],"forms":[8],"of":[9,31,40,73,91,98],"information":[10],"embedded":[11],"in":[12,65,132,154],"spoken":[13],"language,":[14],"including":[15],"linguistic,":[16],"paralinguistic,":[17],"and":[18,60,76,85,115,127,139,152,167,179,186],"non-linguistic":[19],"cues":[20],"that":[21],"are":[22],"vital":[23],"effective":[25],"human-computer":[26],"interaction.":[27],"The":[28],"rapid":[29],"advancement":[30],"large":[32],"language":[33],"models":[34],"(LLMs)":[35],"has":[36],"catalyzed":[37],"emergence":[39],"Large":[42],"Language":[43],"Models":[44],"(Speech":[45],"LLMs),":[46],"which":[47],"marks":[48],"a":[49,78,95,106,174],"transformative":[50],"shift":[51],"toward":[52,182],"general-purpose":[53],"speech":[54,74],"systems.":[56],"To":[57],"further":[58],"clarify":[59],"systematically":[61],"delineate":[62],"task":[63],"objectives,":[64],"this":[66,89,165],"paper,":[67],"we":[68,93,120,142,170],"formally":[69],"define":[70],"concept":[72],"introduce":[77],"structured":[79],"taxonomy":[80],"encompassing":[81],"its":[82],"informational,":[83],"functional,":[84],"format":[86],"dimensions.":[87],"Within":[88],"scope":[90],"definition,":[92],"present":[94],"comprehensive":[96],"review":[97,128],"current":[99],"LLMs,":[101],"analyzing":[102],"their":[103],"architectures":[104],"through":[105],"three-stage":[107],"abstraction:":[108],"Modality":[109,112],"Feature":[110],"Extraction,":[111],"Information":[113],"Fusion,":[114],"LLM":[116],"Inference.":[117],"In":[118],"addition,":[119],"examine":[121],"training":[122],"strategies,":[123],"discuss":[124],"representative":[125],"datasets,":[126],"evaluation":[129],"methodologies":[130],"adopted":[131],"field.":[134],"Based":[135],"on":[136],"empirical":[137],"analyses":[138],"experimental":[140],"evidence,":[141],"identify":[143],"two":[144],"key":[145],"challenges":[146],"currently":[147],"facing":[148],"LLMs-instruction":[150],"sensitivity":[151],"degradation":[153],"semantic":[155],"reasoning-and":[156],"propose":[157],"concrete":[158],"directions":[159],"addressing":[161],"these":[162],"issues.":[163],"Through":[164],"systematic":[166],"detailed":[168],"survey,":[169],"aim":[171],"to":[172],"offer":[173],"foundational":[175],"reference":[176],"researchers":[178],"practitioners":[180],"working":[181],"more":[183],"robust,":[184],"generalizable,":[185],"human-aligned":[187],"LLMs.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-06-12T08:23:45.883708","created_date":"2025-12-04T00:00:00"}
