{"id":"https://openalex.org/W4402111259","doi":"https://doi.org/10.21437/interspeech.2024-1306","title":"DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding","display_name":"DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402111259","doi":"https://doi.org/10.21437/interspeech.2024-1306"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-1306","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1306","pdf_url":"https://www.isca-archive.org/interspeech_2024/shon24_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/interspeech_2024/shon24_interspeech.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020263683","display_name":"Suwon Shon","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Suwon Shon","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052377938","display_name":"Kwangyoun Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kwangyoun Kim","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111487406","display_name":"Yi\u2010Te Hsu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi-Te Hsu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006917911","display_name":"Prashant Sridhar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prashant Sridhar","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5015602781","display_name":"Karen Livescu","orcid":"https://orcid.org/0000-0003-4962-946X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karen Livescu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5020263683"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.808,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.87365455,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4154","last_page":"4158"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9764999747276306,"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/T12031","display_name":"Speech and dialogue systems","score":0.9764999747276306,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9736999869346619,"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":0.954800009727478,"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":0.8120652437210083},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.6959794759750366},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6418087482452393},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5271399021148682},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49823665618896484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49329060316085815}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8120652437210083},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.6959794759750366},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6418087482452393},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5271399021148682},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49823665618896484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49329060316085815}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-1306","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1306","pdf_url":"https://www.isca-archive.org/interspeech_2024/shon24_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2024-1306","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1306","pdf_url":"https://www.isca-archive.org/interspeech_2024/shon24_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402111259.pdf","grobid_xml":"https://content.openalex.org/works/W4402111259.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4306742369","https://openalex.org/W2388125677","https://openalex.org/W4303457083","https://openalex.org/W2131146434","https://openalex.org/W2951359407","https://openalex.org/W4376623224","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0],"integration":[1,20],"of":[2,24,41,98,104],"pre-trained":[3],"text-based":[4],"large":[5],"language":[6],"models":[7],"(LLM)":[8],"with":[9],"speech":[10,18,26,29,43,49,63,70,82,107],"input":[11],"has":[12],"enabled":[13],"instruction-following":[14,88],"capabilities":[15],"for":[16,130],"diverse":[17,36],"tasks.This":[19],"requires":[21],"the":[22,39,56,62,105,120],"use":[23,40],"a":[25,28,68],"encoder,":[27,108],"adapter,":[30],"and":[31,87,123],"an":[32],"LLM,":[33],"trained":[34],"on":[35,81],"tasks.We":[37],"propose":[38],"discrete":[42],"units":[44],"(DSU),":[45],"rather":[46],"than":[47],"continuous-valued":[48],"encoder":[50,71],"outputs,":[51],"that":[52,119],"are":[53,125],"converted":[54],"to":[55],"LLM":[57],"token":[58],"embedding":[59],"space":[60],"using":[61,67],"adapter.We":[64],"generate":[65],"DSU":[66,99],"selfsupervised":[69],"followed":[72],"by":[73],"k-means":[74],"clustering.The":[75],"proposed":[76],"model":[77],"shows":[78],"robust":[79],"performance":[80],"inputs":[83],"from":[84,101],"seen/unseen":[85],"domains":[86],"capability":[89],"in":[90,128],"spoken":[91,131],"question":[92,132],"answering.We":[93],"also":[94],"explore":[95],"various":[96],"types":[97],"extracted":[100],"different":[102],"layers":[103],"self-supervised":[106],"as":[109,111],"well":[110],"Mel":[112],"frequency":[113],"Cepstral":[114],"Coefficients":[115],"(MFCC).Our":[116],"findings":[117],"suggest":[118],"ASR":[121],"task":[122],"datasets":[124],"not":[126],"crucial":[127],"instruction-tuning":[129],"answering":[133],"tasks.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-10T14:07:55.174380","created_date":"2025-10-10T00:00:00"}