{"id":"https://openalex.org/W7148586938","doi":"https://doi.org/10.1109/asru65441.2025.11434765","title":"Transcribe, Translate, or Transliterate: An Investigation of Intermediate Representations in Spoken Language Models","display_name":"Transcribe, Translate, or Transliterate: An Investigation of Intermediate Representations in Spoken Language Models","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148586938","doi":"https://doi.org/10.1109/asru65441.2025.11434765"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434765","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/A5053603914","display_name":"Tol\u00fal\u1ecdpe \u00d2g\u00fanrem\u00ed","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tol\u00fal\u1ecdp\u00e9 \u00d2g\u00fanrem\u00ed","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046006076","display_name":"Christopher D. Manning","orcid":"https://orcid.org/0000-0001-6155-649X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher D. Manning","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087088138","display_name":"Dan Jurafsky","orcid":"https://orcid.org/0000-0002-6459-7745"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Jurafsky","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015602781","display_name":"Karen Livescu","orcid":"https://orcid.org/0000-0003-4962-946X"},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karen Livescu","raw_affiliation_strings":["Toyota Technological Institute at,Chicago"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at,Chicago","institution_ids":["https://openalex.org/I160992636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5053603914"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87580625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.5516999959945679,"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":0.5516999959945679,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.10369999706745148,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.05389999970793724,"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/spoken-language","display_name":"Spoken language","score":0.6583999991416931},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5961999893188477},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5672000050544739},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5170999765396118},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.49900001287460327},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.48510000109672546},{"id":"https://openalex.org/keywords/phonetics","display_name":"Phonetics","score":0.47760000824928284},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.35839998722076416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7696999907493591},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.6583999991416931},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6218000054359436},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6015999913215637},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5961999893188477},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5672000050544739},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5170999765396118},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.510200023651123},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.49900001287460327},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48510000109672546},{"id":"https://openalex.org/C137584468","wikidata":"https://www.wikidata.org/wiki/Q35395","display_name":"Phonetics","level":2,"score":0.47760000824928284},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3982999920845032},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.35839998722076416},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.31850001215934753},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C17137986","wikidata":"https://www.wikidata.org/wiki/Q215067","display_name":"Orthogonality","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.27390000224113464},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.25870001316070557}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434765","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":[{"display_name":"Quality Education","score":0.782414436340332,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1854884267","https://openalex.org/W2747874407","https://openalex.org/W3155609600","https://openalex.org/W3162133897","https://openalex.org/W3169369929","https://openalex.org/W3198275944","https://openalex.org/W3198815374","https://openalex.org/W4225096077","https://openalex.org/W4226380987","https://openalex.org/W4287887669","https://openalex.org/W4385823003","https://openalex.org/W4389518334","https://openalex.org/W4391021627","https://openalex.org/W4394773771","https://openalex.org/W4402671241","https://openalex.org/W4402671717","https://openalex.org/W7133239970"],"related_works":[],"abstract_inverted_index":{"Spoken":[0],"language":[1,9],"models":[2,10,79,107],"(SLMs)":[3],"that":[4,27,108,128],"integrate":[5],"speech":[6,22,135,141],"with":[7,123],"large":[8],"(LMs)":[11],"rely":[12],"on":[13,132],"modality":[14],"adapters":[15],"(MAs)":[16],"to":[17,24,30,67,86,99],"map":[18],"the":[19,31,49,62,88,91,116,119,134],"output":[20,51],"of":[21,90,118],"encoders":[23],"a":[25,81],"representation":[26,52],"is":[28,137],"understandable":[29],"decoder":[32,64],"LM.":[33],"Yet":[34],"we":[35,47,71],"know":[36],"very":[37],"little":[38],"about":[39],"how":[40],"these":[41],"crucial":[42],"MAs":[43,84,113],"transform":[44],"representations.":[45,77],"Here":[46],"examine":[48],"MA":[50,69,76],"in":[53,103],"three":[54],"SLMs":[55],"(SALMONN,":[56],"Qwen2-Audio":[57],"and":[58],"Phi-4-Multimodal-Instruct).":[59],"By":[60],"finding":[61],"nearest":[63],"LM":[65],"token":[66],"an":[68,94],"representation,":[70],"uncover":[72],"two":[73],"strategies":[74],"for":[75,140,145],"For":[78,106],"using":[80,93],"Whisper":[82],"encoder,":[83],"appear":[85],"represent":[87,115],"meaning":[89],"input":[92],"English-based":[95],"interlingua,":[96],"allowing":[97],"them":[98],"handle":[100],"languages":[101],"unseen":[102],"instruction":[104],"tuning.":[105],"don\u2019":[109],"t,":[110],"like":[111],"Phi-4-Multimodal-Instruct,":[112],"instead":[114],"phonetics":[117],"input,":[120],"but":[121],"expressed":[122],"English":[124],"words.":[125],"We":[126],"hypothesize":[127],"which":[129],"arises":[130],"depends":[131],"whether":[133],"encoder":[136],"trained":[138],"only":[139],"recognition":[142],"or":[143],"also":[144],"translation.":[146]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}