{"id":"https://openalex.org/W7148464209","doi":"https://doi.org/10.1109/asru65441.2025.11434630","title":"Flow-SLM: Joint Learning of Linguistic and Acoustic Information for Spoken Language Modeling","display_name":"Flow-SLM: Joint Learning of Linguistic and Acoustic Information for Spoken Language Modeling","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148464209","doi":"https://doi.org/10.1109/asru65441.2025.11434630"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434630","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/A5049062211","display_name":"Ju-Chieh Chou","orcid":null},"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":true,"raw_author_name":"Ju-Chieh Chou","raw_affiliation_strings":["Toyota Technological Institute at Chicago IL,USA"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago IL,USA","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101805947","display_name":"Jiawei Zhou","orcid":"https://orcid.org/0000-0001-5590-6270"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiawei Zhou","raw_affiliation_strings":["Stony Brook University,NY,USA"],"affiliations":[{"raw_affiliation_string":"Stony Brook University,NY,USA","institution_ids":["https://openalex.org/I59553526"]}]},{"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 IL,USA"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago IL,USA","institution_ids":["https://openalex.org/I160992636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5049062211"],"corresponding_institution_ids":["https://openalex.org/I160992636"],"apc_list":null,"apc_paid":null,"fwci":2.1819,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.92937694,"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/T12031","display_name":"Speech and dialogue systems","score":0.21879999339580536,"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":0.21879999339580536,"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":0.1404000073671341,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.06790000200271606,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6118999719619751},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.6083999872207642},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3425999879837036},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.28279998898506165},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2671000063419342}],"concepts":[{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6118999719619751},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.6083999872207642},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5738999843597412},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.570900022983551},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4449000060558319},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41260001063346863},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32499998807907104},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.30809998512268066},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.2651999890804291},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434630","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.704470157623291}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W3095410713","https://openalex.org/W3140429000","https://openalex.org/W3198217962","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3210177631","https://openalex.org/W3215615641","https://openalex.org/W4381786045","https://openalex.org/W4385823432","https://openalex.org/W4389518827","https://openalex.org/W4391021755","https://openalex.org/W4392904805","https://openalex.org/W4392931276","https://openalex.org/W4402669711","https://openalex.org/W4406461681","https://openalex.org/W4408352488","https://openalex.org/W4412888269"],"related_works":[],"abstract_inverted_index":{"Textless":[0],"spoken":[1],"language":[2],"models":[3,7,48,129],"(SLMs)":[4],"are":[5],"generative":[6],"of":[8,30,83,107,132],"speech":[9],"that":[10,112],"do":[11],"not":[12],"rely":[13,34],"on":[14,35,98],"text":[15],"supervision.":[16],"Most":[17],"textless":[18],"SLMs":[19],"learn":[20],"to":[21,39,43,52,67,92,127],"predict":[22,93],"the":[23,44,84,94,99,104],"next":[24],"semantic":[25,76,100,116],"token,":[26],"a":[27,36,79,89],"discrete":[28],"representation":[29,82],"linguistic":[31,70,120,133],"content,":[32],"and":[33,55,71,78,110],"separate":[37],"vocoder":[38],"add":[40],"acoustic":[41,53,60,72,85,139],"information":[42,73],"generated":[45],"speech.":[46],"Such":[47],"have":[49],"no":[50,56],"access":[51],"context":[54],"built-in":[57],"control":[58],"over":[59],"details.":[61],"In":[62],"this":[63,108],"work,":[64],"we":[65],"propose":[66],"jointly":[68],"model":[69],"by":[74],"generating":[75],"tokens":[77,117],"continuous":[80,95],"real-valued":[81],"frame.":[86],"We":[87,102],"use":[88],"flow-matching":[90],"objective":[91],"vector":[96],"conditioned":[97],"tokens.":[101],"study":[103],"design":[105],"space":[106],"approach":[109,123],"find":[111],"predicting":[113],"multiple":[114],"future":[115],"helps":[118],"preserve":[119],"information.":[121],"Our":[122],"achieves":[124],"comparable":[125],"performance":[126],"existing":[128],"in":[130,141],"terms":[131],"likelihood":[134],"benchmarks,":[135],"while":[136],"providing":[137],"better":[138],"detail":[140],"prompted":[142],"generation.<sup":[143],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[144,146],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup><sup":[145],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>Demo":[147],"page:":[148],"https://jjery2243542.github.io/flowslm.github.io/":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2026-04-03T00:00:00"}