{"id":"https://openalex.org/W3025324327","doi":"https://doi.org/10.21437/interspeech.2020-1246","title":"Speech to Text Adaptation: Towards an Efficient Cross-Modal Distillation","display_name":"Speech to Text Adaptation: Towards an Efficient Cross-Modal Distillation","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3025324327","doi":"https://doi.org/10.21437/interspeech.2020-1246","mag":"3025324327"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1246","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1246","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2005.08213","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102984975","display_name":"Won Ik Cho","orcid":"https://orcid.org/0000-0002-8882-9125"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Won Ik Cho","raw_affiliation_strings":["Seoul National Univ.#TAB#"],"affiliations":[{"raw_affiliation_string":"Seoul National Univ.#TAB#","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005340561","display_name":"Donghyun Kwak","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Donghyun Kwak","raw_affiliation_strings":["NAVER CORPORATION"],"affiliations":[{"raw_affiliation_string":"NAVER CORPORATION","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016783920","display_name":"Ji Won Yoon","orcid":"https://orcid.org/0000-0001-8631-4489"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ji Won Yoon","raw_affiliation_strings":["Seoul National Univ.#TAB#"],"affiliations":[{"raw_affiliation_string":"Seoul National Univ.#TAB#","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051356511","display_name":"Nam Soo Kim","orcid":"https://orcid.org/0000-0002-0568-4902"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nam Soo Kim","raw_affiliation_strings":["Seoul National Univ.#TAB#"],"affiliations":[{"raw_affiliation_string":"Seoul National Univ.#TAB#","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102984975"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.4115,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.68678598,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"896","last_page":"900"},"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":0.9986000061035156,"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":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.8801186084747314},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5902038216590881},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5611969828605652},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5041061639785767},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.488238126039505},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45218250155448914},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4226142466068268},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.4162459671497345},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41161084175109863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8801186084747314},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5902038216590881},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5611969828605652},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5041061639785767},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.488238126039505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45218250155448914},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4226142466068268},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4162459671497345},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41161084175109863},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-1246","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1246","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2005.08213","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.08213","pdf_url":"https://arxiv.org/pdf/2005.08213","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3025324327","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2005.08213.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2005.08213","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2005.08213","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2005.08213","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.08213","pdf_url":"https://arxiv.org/pdf/2005.08213","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3025324327.pdf","grobid_xml":"https://content.openalex.org/works/W3025324327.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W753847829","https://openalex.org/W1494198834","https://openalex.org/W1575321350","https://openalex.org/W1821462560","https://openalex.org/W2077302143","https://openalex.org/W2131774270","https://openalex.org/W2525778437","https://openalex.org/W2739879705","https://openalex.org/W2785350307","https://openalex.org/W2787560479","https://openalex.org/W2924902521","https://openalex.org/W2928075308","https://openalex.org/W2932319281","https://openalex.org/W2936848022","https://openalex.org/W2946345909","https://openalex.org/W2949079242","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963974889","https://openalex.org/W2964052309","https://openalex.org/W2967985939","https://openalex.org/W2981458636","https://openalex.org/W2981818381","https://openalex.org/W2990149993","https://openalex.org/W2998386507","https://openalex.org/W3004603414","https://openalex.org/W3015412890","https://openalex.org/W3026408381","https://openalex.org/W3105966348","https://openalex.org/W3156828761"],"related_works":["https://openalex.org/W3097414768","https://openalex.org/W3093529776","https://openalex.org/W3162646066","https://openalex.org/W3142434946","https://openalex.org/W3097301532","https://openalex.org/W2891229414","https://openalex.org/W3005420083","https://openalex.org/W2109461733","https://openalex.org/W2096192176","https://openalex.org/W1488433060","https://openalex.org/W2155448060","https://openalex.org/W2407151108","https://openalex.org/W198170052","https://openalex.org/W2045802514","https://openalex.org/W2612603407","https://openalex.org/W2963288440","https://openalex.org/W2999245659","https://openalex.org/W3022526310","https://openalex.org/W2097550833","https://openalex.org/W1941246423"],"abstract_inverted_index":{"Speech":[0,134],"is":[1,11,169],"one":[2],"of":[3,8,13,19,29,68,90,126,156],"the":[4,17,26,43,60,66,82,88,98,124,130,147,153,157,166,173],"most":[5],"effective":[6],"means":[7],"communication":[9],"and":[10,72],"full":[12],"information":[14],"that":[15,58,78,146],"helps":[16],"transmission":[18],"utterer's":[20],"thoughts.":[21],"However,":[22],"mainly":[23],"due":[24],"to":[25,106,159,171],"cumbersome":[27],"processing":[28],"acoustic":[30],"features,":[31],"phoneme":[32],"or":[33],"word":[34],"posterior":[35],"probability":[36],"has":[37],"frequently":[38],"been":[39],"discarded":[40],"in":[41,79,164],"understanding":[42,51],"natural":[44],"language.":[45],"Thus,":[46],"some":[47],"recent":[48,118],"spoken":[49],"language":[50,93],"(SLU)":[52],"modules":[53],"have":[54],"utilized":[55],"end-to-end":[56],"structures":[57],"preserve":[59],"uncertainty":[61],"information.":[62],"This":[63],"further":[64],"reduces":[65],"propagation":[67],"speech":[69,83,168],"recognition":[70],"error":[71],"guarantees":[73],"computational":[74],"efficiency.":[75],"We":[76,96,122],"claim":[77],"this":[80],"process,":[81],"comprehension":[84],"can":[85,111],"benefit":[86],"from":[87,100,152],"inference":[89],"massive":[91],"pre-trained":[92],"models":[94],"(LMs).":[95],"transfer":[97],"knowledge":[99,148],"a":[101,113,160],"concrete":[102],"Transformer-based":[103],"text":[104],"LM":[105,158],"an":[107,136],"SLU":[108,138],"module":[109],"which":[110,165],"face":[112],"data":[114],"shortage,":[115],"based":[116],"on":[117,132],"cross-modal":[119],"distillation":[120],"methodologies.":[121],"demonstrate":[123],"validity":[125],"our":[127,144],"proposal":[128],"upon":[129],"performance":[131],"Fluent":[133],"Command,":[135],"English":[137],"benchmark.":[139],"Thereby,":[140],"we":[141],"experimentally":[142],"verify":[143],"hypothesis":[145],"could":[149],"be":[150],"shared":[151],"top":[154],"layer":[155],"fully":[161],"speech-based":[162],"module,":[163],"abstracted":[167],"expected":[170],"meet":[172],"semantic":[174],"representation.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}