{"id":"https://openalex.org/W4375869174","doi":"https://doi.org/10.1109/icassp49357.2023.10096950","title":"Adaptive Knowledge Distillation Between Text and Speech Pre-Trained Models","display_name":"Adaptive Knowledge Distillation Between Text and Speech Pre-Trained Models","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869174","doi":"https://doi.org/10.1109/icassp49357.2023.10096950"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096950","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096950","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5072407590","display_name":"Jinjie Ni","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG","US"],"is_corresponding":true,"raw_author_name":"Jinjie Ni","raw_affiliation_strings":["Alibaba Group","School of Computer Science and Engineering, Nanyang Technological University"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101568886","display_name":"Yukun Ma","orcid":"https://orcid.org/0000-0002-4419-4287"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yukun Ma","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396375","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0002-0356-1968"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen Wang","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100428456","display_name":"Qian Chen","orcid":"https://orcid.org/0000-0002-1909-302X"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qian Chen","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104217727","display_name":"Dianwen Ng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG","US"],"is_corresponding":false,"raw_author_name":"Dianwen Ng","raw_affiliation_strings":["Alibaba Group","School of Computer Science and Engineering, Nanyang Technological University"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101913177","display_name":"Lei Han","orcid":"https://orcid.org/0000-0001-8686-8940"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Han Lei","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering","School of Computer Science and Engineering, Nanyang Technological University"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101562097","display_name":"Trung Hieu Nguyen","orcid":"https://orcid.org/0000-0002-2683-253X"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trung Hieu Nguyen","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100393899","display_name":"Chong Zhang","orcid":"https://orcid.org/0000-0002-2162-4344"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chong Zhang","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749735","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0002-9223-9654"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100752356","display_name":"Erik Cambria","orcid":"https://orcid.org/0000-0002-3030-1280"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Erik Cambria","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering","School of Computer Science and Engineering, Nanyang Technological University"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5072407590"],"corresponding_institution_ids":["https://openalex.org/I172675005","https://openalex.org/I4210095624"],"apc_list":null,"apc_paid":null,"fwci":0.533,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.7048367,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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":0.9994000196456909,"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":0.9975000023841858,"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":0.7837324142456055},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.7475817799568176},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6636146306991577},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6287108659744263},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.584228515625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5502238869667053},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5338785648345947},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5212788581848145},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4241068363189697},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4145345091819763},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3789794445037842}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7837324142456055},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.7475817799568176},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6636146306991577},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6287108659744263},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.584228515625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5502238869667053},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5338785648345947},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5212788581848145},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4241068363189697},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4145345091819763},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3789794445037842},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096950","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096950","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2896457183","https://openalex.org/W2965373594","https://openalex.org/W2973049979","https://openalex.org/W2996428491","https://openalex.org/W3006683367","https://openalex.org/W3034837210","https://openalex.org/W3036601975","https://openalex.org/W3096589040","https://openalex.org/W3098169801","https://openalex.org/W3148001440","https://openalex.org/W3171345413","https://openalex.org/W3197580070","https://openalex.org/W3205644108","https://openalex.org/W3207222250","https://openalex.org/W3209059054","https://openalex.org/W4221142780","https://openalex.org/W4221155340","https://openalex.org/W4288089799","https://openalex.org/W4307009360","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6768021236","https://openalex.org/W6769627184","https://openalex.org/W6774054309","https://openalex.org/W6780218876","https://openalex.org/W6780585982","https://openalex.org/W6796724269","https://openalex.org/W6803092890","https://openalex.org/W6810259195"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2378857091","https://openalex.org/W2999756192","https://openalex.org/W103652678","https://openalex.org/W4226090359","https://openalex.org/W2059697060","https://openalex.org/W936373746","https://openalex.org/W4382701072","https://openalex.org/W4256502920"],"abstract_inverted_index":{"Learning":[0],"on":[1,36,137],"a":[2,74],"massive":[3],"amount":[4,76],"of":[5,13,39,68,77,116],"speech":[6,16,55,71,93,132],"corpus":[7],"leads":[8],"to":[9,48,63,122,143],"the":[10,27,49,65,81,85,101,105],"recent":[11],"success":[12],"many":[14],"self-supervised":[15],"models.":[17,134],"With":[18],"knowledge":[19,28,108,153],"distillation,":[20,102],"these":[21],"models":[22,32],"may":[23],"also":[24],"benefit":[25],"from":[26],"encoded":[29],"by":[30],"language":[31,140],"that":[33,111,145],"are":[34],"pre-trained":[35,133],"rich":[37],"sources":[38],"texts.":[40],"The":[41],"distillation":[42,62,157],"process,":[43],"however,":[44],"is":[45,147],"challenging":[46],"due":[47],"modal":[50],"disparity":[51],"between":[52,90,129],"textual":[53],"and":[54,70,87,92,119,126,131],"embedding":[56,66],"spaces.":[57],"This":[58],"paper":[59],"studies":[60],"metric-based":[61,156],"align":[64],"space":[67],"text":[69,91,130],"with":[72],"only":[73],"small":[75],"data":[78],"without":[79],"modifying":[80],"model":[82],"structure.":[83],"Since":[84],"semantic":[86],"granularity":[88,118],"gap":[89],"has":[94],"been":[95],"omitted":[96],"in":[97,150],"literature,":[98],"which":[99],"impairs":[100],"we":[103],"propose":[104],"Prior-informed":[106],"Adaptive":[107],"Distillation":[109],"(PAD)":[110],"adaptively":[112],"leverages":[113],"text/speech":[114],"units":[115],"variable":[117],"prior":[120],"distributions":[121],"achieve":[123],"better":[124],"global":[125],"local":[127],"alignments":[128],"We":[135],"evaluate":[136],"three":[138],"spoken":[139],"understanding":[141],"benchmarks":[142],"show":[144],"PAD":[146],"more":[148],"effective":[149],"transferring":[151],"linguistic":[152],"than":[154],"other":[155],"approaches.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}