{"id":"https://openalex.org/W4392904094","doi":"https://doi.org/10.1109/icassp48485.2024.10448022","title":"Multiple Representation Transfer from Large Language Models to End-to-End ASR Systems","display_name":"Multiple Representation Transfer from Large Language Models to End-to-End ASR Systems","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904094","doi":"https://doi.org/10.1109/icassp48485.2024.10448022"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5067751383","display_name":"Takuma Udagawa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takuma Udagawa","raw_affiliation_strings":["IBM Research AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028421346","display_name":"Masayuki Suzuki","orcid":"https://orcid.org/0000-0002-0436-1490"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masayuki Suzuki","raw_affiliation_strings":["IBM Research AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021294422","display_name":"Gakuto Kurata","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gakuto Kurata","raw_affiliation_strings":["IBM Research AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004152333","display_name":"Masayasu Muraoka","orcid":"https://orcid.org/0009-0004-3620-1231"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masayasu Muraoka","raw_affiliation_strings":["IBM Research AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"George Saon","raw_affiliation_strings":["IBM Research AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10176","last_page":"10180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9993000030517578,"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":0.9993000030517578,"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/representation","display_name":"Representation (politics)","score":0.8102520704269409},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7461400628089905},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5045150518417358},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.487409383058548},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4751734137535095},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4408376216888428},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4246114194393158},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32779669761657715},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11245104670524597}],"concepts":[{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.8102520704269409},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7461400628089905},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5045150518417358},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.487409383058548},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4751734137535095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4408376216888428},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4246114194393158},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32779669761657715},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11245104670524597},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2144499799","https://openalex.org/W2750499125","https://openalex.org/W2923014074","https://openalex.org/W2946417913","https://openalex.org/W2963362078","https://openalex.org/W2970454332","https://openalex.org/W2978017171","https://openalex.org/W3008037978","https://openalex.org/W3016240723","https://openalex.org/W3024308166","https://openalex.org/W3034775979","https://openalex.org/W3035390927","https://openalex.org/W3096297644","https://openalex.org/W3097777922","https://openalex.org/W3105966348","https://openalex.org/W3122931219","https://openalex.org/W3141961557","https://openalex.org/W3155427814","https://openalex.org/W3163300396","https://openalex.org/W3164692279","https://openalex.org/W3196313137","https://openalex.org/W3200601846","https://openalex.org/W3200786561","https://openalex.org/W4224916448","https://openalex.org/W4225299129","https://openalex.org/W4297841367","https://openalex.org/W4319862680","https://openalex.org/W4372260576","https://openalex.org/W4381827575","https://openalex.org/W4385567350","https://openalex.org/W4385567464","https://openalex.org/W4385823005","https://openalex.org/W4389010951","https://openalex.org/W4389519317","https://openalex.org/W6638523607","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6768851824","https://openalex.org/W6770528390","https://openalex.org/W6778883912","https://openalex.org/W6779271971","https://openalex.org/W6790163761","https://openalex.org/W6810738896","https://openalex.org/W6845595086","https://openalex.org/W6853998256"],"related_works":["https://openalex.org/W1585007175","https://openalex.org/W2382521049","https://openalex.org/W2144385241","https://openalex.org/W4300101996","https://openalex.org/W2165950148","https://openalex.org/W4253593777","https://openalex.org/W2951497643","https://openalex.org/W4403053866","https://openalex.org/W2142393343","https://openalex.org/W2338854850"],"abstract_inverted_index":{"Transferring":[0],"the":[1,34,41],"knowledge":[2,15],"of":[3,31,37,43,68,76,93],"large":[4],"language":[5],"models":[6],"(LLMs)":[7],"is":[8,46],"a":[9,28,44,65,79,103],"promising":[10],"technique":[11],"to":[12,70,100],"incorporate":[13],"linguistic":[14],"into":[16,78],"end-to-end":[17],"automatic":[18],"speech":[19],"recognition":[20],"(ASR)":[21],"systems.":[22],"However,":[23],"existing":[24],"works":[25],"only":[26,102],"transfer":[27,73],"single":[29,104],"representation":[30,42],"LLM":[32,105],"(e.g.":[33],"last":[35],"layer":[36],"pretrained":[38],"BERT),":[39],"while":[40],"text":[45],"inherently":[47],"non-unique":[48],"and":[49,58,72],"can":[50,95],"be":[51,96],"obtained":[52],"variously":[53],"from":[54],"different":[55],"layers,":[56],"contexts":[57],"models.":[59],"In":[60],"this":[61],"work,":[62],"we":[63,87],"explore":[64],"wide":[66],"range":[67],"techniques":[69],"obtain":[71],"multiple":[74,91],"representations":[75,92],"LLMs":[77,94],"transducer-based":[80],"ASR":[81],"system.":[82],"While":[83],"being":[84],"conceptually":[85],"simple,":[86],"show":[88],"that":[89],"transferring":[90,101],"an":[97],"effective":[98],"alternative":[99],"representation.":[106]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
