{"id":"https://openalex.org/W7148395512","doi":"https://doi.org/10.1109/asru65441.2025.11434740","title":"Evaluating Self-Supervised Speech Models Via Text-Based LLMs","display_name":"Evaluating Self-Supervised Speech Models Via Text-Based LLMs","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148395512","doi":"https://doi.org/10.1109/asru65441.2025.11434740"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434740","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/A5059612504","display_name":"Takashi Maekaku","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takashi Maekaku","raw_affiliation_strings":["LY Corporation,Tokyo,JAPAN"],"affiliations":[{"raw_affiliation_string":"LY Corporation,Tokyo,JAPAN","institution_ids":["https://openalex.org/I4210096607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103518557","display_name":"Keita Goto","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keita Goto","raw_affiliation_strings":["LY Corporation,Tokyo,JAPAN"],"affiliations":[{"raw_affiliation_string":"LY Corporation,Tokyo,JAPAN","institution_ids":["https://openalex.org/I4210096607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132801711","display_name":"Jinchuan Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinchuan Tian","raw_affiliation_strings":["Carnegie Mellon University,PA,USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,PA,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109365728","display_name":"Yusuke Shinohara","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Shinohara","raw_affiliation_strings":["LY Corporation,Tokyo,JAPAN"],"affiliations":[{"raw_affiliation_string":"LY Corporation,Tokyo,JAPAN","institution_ids":["https://openalex.org/I4210096607"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132789061","display_name":"Shinji Watanabe","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,PA,USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,PA,USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5059612504"],"corresponding_institution_ids":["https://openalex.org/I4210096607"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87561989,"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":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8701000213623047,"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":0.8701000213623047,"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":0.03020000085234642,"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":0.011800000444054604,"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/rendering","display_name":"Rendering (computer graphics)","score":0.516700029373169},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.446399986743927},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4341999888420105},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.43209999799728394},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.35670000314712524},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.3562000095844269},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.349700003862381}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6955999732017517},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.516700029373169},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4975000023841858},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4722999930381775},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.446399986743927},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4341999888420105},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.43209999799728394},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41269999742507935},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.35670000314712524},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.3562000095844269},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34130001068115234},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.2515999972820282},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434740","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":[{"score":0.562006950378418,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W108866686","https://openalex.org/W1494198834","https://openalex.org/W2079735306","https://openalex.org/W2395899413","https://openalex.org/W2953190524","https://openalex.org/W2962800603","https://openalex.org/W2981087920","https://openalex.org/W3162133897","https://openalex.org/W3197259906","https://openalex.org/W3197580070","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3213029956","https://openalex.org/W4226380987","https://openalex.org/W4249992252","https://openalex.org/W4281492411","https://openalex.org/W4313015712","https://openalex.org/W4375869259","https://openalex.org/W4385822439","https://openalex.org/W4401281176","https://openalex.org/W4404782746"],"related_works":[],"abstract_inverted_index":{"Self-Supervised":[0],"Learning":[1],"(SSL)":[2],"has":[3],"gained":[4],"traction":[5],"for":[6,40,132],"its":[7],"ability":[8],"to":[9,30],"learn":[10],"rich":[11],"representations":[12],"with":[13],"low":[14],"labeling":[15],"costs,":[16],"applicable":[17],"across":[18],"diverse":[19],"downstream":[20],"tasks.":[21],"However,":[22],"assessing":[23],"the":[24,31,78,87],"downstream-task":[25],"performance":[26],"remains":[27],"challenging":[28],"due":[29],"cost":[32],"of":[33],"extra":[34,45,92],"training":[35,46,93],"and":[36,66,105],"evaluation.":[37],"Existing":[38],"methods":[39],"task-agnostic":[41],"evaluation":[42,54,122],"also":[43,125],"require":[44],"or":[47,94],"hyper-parameter":[48],"tuning.":[49,96],"We":[50],"propose":[51],"a":[52,100],"novel":[53],"metric":[55],"using":[56],"large":[57],"language":[58],"models":[59,73],"(LLMs).":[60],"By":[61],"inputting":[62],"discrete":[63],"token":[64],"sequences":[65],"minimal":[67],"domain":[68],"cues":[69,82],"derived":[70],"from":[71],"SSL":[72,121],"into":[74],"LLMs,":[75],"we":[76],"obtain":[77],"mean":[79],"log-likelihood;":[80],"these":[81],"guide":[83],"in-context":[84],"learning,":[85],"rendering":[86],"score":[88],"more":[89],"reliable":[90],"without":[91],"hyperparameter":[95],"Experimental":[97],"results":[98],"show":[99],"correlation":[101],"between":[102],"LLM-based":[103],"scores":[104],"automatic":[106],"speech":[107],"recognition":[108],"task.":[109,135],"Additionally,":[110],"our":[111],"findings":[112],"reveal":[113],"that":[114,129],"LLMs":[115],"not":[116],"only":[117],"functions":[118],"as":[119],"an":[120],"tools":[123],"but":[124],"provides":[126],"inference-time":[127],"embeddings":[128],"are":[130],"useful":[131],"speaker":[133],"verification":[134]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}