{"id":"https://openalex.org/W7148261585","doi":"https://doi.org/10.1109/asru65441.2025.11434631","title":"Bridging the Modality Gap: Softly Discretizing Audio Representation for LLM-based Automatic Speech Recognition","display_name":"Bridging the Modality Gap: Softly Discretizing Audio Representation for LLM-based Automatic Speech Recognition","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148261585","doi":"https://doi.org/10.1109/asru65441.2025.11434631"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5132830280","display_name":"Mu Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mu Yang","raw_affiliation_strings":["University of Texas at Dallas,Centor for Robust Speech Systems (CRSS),USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas,Centor for Robust Speech Systems (CRSS),USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065795147","display_name":"Szu-Jui Chen","orcid":"https://orcid.org/0000-0002-6406-9280"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Szu-Jui Chen","raw_affiliation_strings":["University of Texas at Dallas,Centor for Robust Speech Systems (CRSS),USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas,Centor for Robust Speech Systems (CRSS),USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101151982","display_name":"Jiamin Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiamin Xie","raw_affiliation_strings":["University of Texas at Dallas,Centor for Robust Speech Systems (CRSS),USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas,Centor for Robust Speech Systems (CRSS),USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132795248","display_name":"H. L. John Hansen","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H. L. John Hansen","raw_affiliation_strings":["University of Texas at Dallas,Centor for Robust Speech Systems (CRSS),USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas,Centor for Robust Speech Systems (CRSS),USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5132830280"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":2.1819,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.92935199,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9384999871253967,"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":0.9384999871253967,"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/T10860","display_name":"Speech and Audio Processing","score":0.041600000113248825,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.005499999970197678,"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/codebook","display_name":"Codebook","score":0.8604999780654907},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.6211000084877014},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.6208999752998352},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5857999920845032},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.566100001335144},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5231999754905701},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5105999708175659},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4788999855518341},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4724000096321106}],"concepts":[{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.8604999780654907},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7218999862670898},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6962000131607056},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.6211000084877014},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.6208999752998352},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5857999920845032},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.566100001335144},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5231999754905701},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5105999708175659},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5105999708175659},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4788999855518341},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4724000096321106},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.3978999853134155},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3815000057220459},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.33009999990463257},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.2728999853134155},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26269999146461487},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.2574000060558319},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2572999894618988}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W3209984917","https://openalex.org/W4385245566","https://openalex.org/W4390224291","https://openalex.org/W4391021666","https://openalex.org/W4391021773","https://openalex.org/W4392903956","https://openalex.org/W4392931626","https://openalex.org/W4402112335","https://openalex.org/W4402112398","https://openalex.org/W4410771025","https://openalex.org/W4411120458","https://openalex.org/W4415433014"],"related_works":[],"abstract_inverted_index":{"One":[0],"challenge":[1],"of":[2,19,27,95,135],"integrating":[3,38],"speech":[4,45],"input":[5],"with":[6,68],"large":[7],"language":[8],"models":[9],"(LLMs)":[10],"stems":[11],"from":[12,64],"the":[13,16,23,49,54,57,61,65,69,74,86,96,101,109,122,133],"discrepancy":[14],"between":[15],"continuous":[17,62],"nature":[18],"audio":[20,66,81,97],"data":[21],"and":[22,103],"discrete":[24,70],"tokenbased":[25],"paradigm":[26],"LLMs.":[28],"To":[29],"mitigate":[30],"this":[31],"gap,":[32],"we":[33],"propose":[34],"a":[35,79,92,105,139],"method":[36,118],"for":[37],"vector":[39],"quantization":[40],"(VQ)":[41],"into":[42],"LLM-based":[43,143],"automatic":[44],"recognition":[46],"(ASR).":[47],"Using":[48],"LLM":[50,71,75],"embedding":[51],"table":[52],"as":[53,138],"VQ":[55,58],"codebook,":[56],"module":[59],"aligns":[60],"representations":[63],"encoder":[67],"inputs,":[72],"enabling":[73],"to":[76],"operate":[77],"on":[78],"discretized":[80],"representation":[82,98],"that":[83,115],"better":[84],"reflects":[85],"linguistic":[87],"structure.":[88],"We":[89],"further":[90],"create":[91],"\u201csoft":[93],"discretization\u201d":[94],"by":[99],"updating":[100],"codebook":[102,110],"performing":[104],"weighted":[106],"sum":[107],"over":[108],"embeddings.":[111],"Empirical":[112],"results":[113],"demonstrate":[114],"our":[116],"proposed":[117],"significantly":[119],"improves":[120],"upon":[121],"LLMbased":[123],"ASR":[124],"baseline,":[125],"particularly":[126],"in":[127,142],"out-of-domain":[128],"conditions.":[129],"This":[130],"work":[131],"highlights":[132],"potential":[134],"soft":[136],"discretization":[137],"modality":[140],"bridge":[141],"ASR.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2026-04-03T00:00:00"}