{"id":"https://openalex.org/W4375869421","doi":"https://doi.org/10.1109/icassp49357.2023.10097130","title":"Auxiliary Pooling Layer For Spoken Language Understanding","display_name":"Auxiliary Pooling Layer For Spoken Language Understanding","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869421","doi":"https://doi.org/10.1109/icassp49357.2023.10097130"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097130","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10097130","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":"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/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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072407590","display_name":"Jinjie Ni","orcid":null},"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":"Jinjie Ni","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering","School of Computer Science and Engineering, Nanyang Technological University"],"raw_orcid":null,"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/A5007695285","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0003-1867-0937"},"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"],"raw_orcid":null,"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"],"raw_orcid":null,"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9991000294685364,"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":0.8538572192192078},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7136080265045166},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.7053596377372742},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6777019500732422},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6475039720535278},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6086537837982178},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5755029916763306},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5334954857826233},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5086432695388794},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.45933476090431213},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.41531887650489807},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.4136059880256653}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8538572192192078},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7136080265045166},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.7053596377372742},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6777019500732422},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6475039720535278},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6086537837982178},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5755029916763306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5334954857826233},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5086432695388794},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45933476090431213},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41531887650489807},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.4136059880256653},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097130","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10097130","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2146334809","https://openalex.org/W2972584841","https://openalex.org/W3036601975","https://openalex.org/W3097777922","https://openalex.org/W3148001440","https://openalex.org/W3161223924","https://openalex.org/W3164692279","https://openalex.org/W3197580070","https://openalex.org/W3203399231","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3212456749","https://openalex.org/W3215155711","https://openalex.org/W4221142780","https://openalex.org/W4284677487","https://openalex.org/W4284973286","https://openalex.org/W4297841528","https://openalex.org/W6780218876","https://openalex.org/W6801910562","https://openalex.org/W6803953248","https://openalex.org/W6809878971","https://openalex.org/W6839026989","https://openalex.org/W6839482795"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2931688134","https://openalex.org/W2626256601","https://openalex.org/W2377919138","https://openalex.org/W2468279273","https://openalex.org/W147410782","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W2378857091","https://openalex.org/W2999756192"],"abstract_inverted_index":{"End-to-end":[0],"spoken":[1,106],"language":[2,107],"understanding":[3],"requires":[4],"speech":[5,24,29,39,77],"data":[6,25],"annotated":[7,18],"with":[8,55,90],"semantic":[9,43],"information":[10,89],"and":[11],"may":[12],"suffer":[13],"from":[14,50,74],"the":[15,37,68,87,91,98],"shortage":[16],"of":[17,100,105],"data.":[19],"Recent":[20],"progresses":[21],"leverage":[22],"unlabelled":[23],"to":[26,41,76],"pre-train":[27],"a":[28,34,51,60],"encoder.":[30],"However,":[31],"it":[32],"remains":[33],"challenge":[35],"for":[36],"pre-trained":[38,52],"encoder":[40],"encode":[42],"information.":[44],"Existing":[45],"works":[46],"explore":[47],"transferring":[48,72],"knowledge":[49,73],"text":[53],"model":[54],"different":[56],"alignment":[57],"losses":[58],"at":[59],"fixed":[61],"granularity.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66],"address":[67],"variable":[69],"granularity":[70],"in":[71],"texts":[75],"representation":[78],"via":[79],"APLY,":[80],"an":[81],"auxiliary":[82],"pooling":[83],"layer,":[84],"that":[85],"fuses":[86],"global":[88],"adaptively":[92],"encoded":[93],"local":[94],"context.":[95],"We":[96],"demonstrate":[97],"effectiveness":[99],"APLY":[101],"on":[102],"three":[103],"benchmarks":[104],"understanding.":[108]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}