{"id":"https://openalex.org/W3163044982","doi":"https://doi.org/10.1109/icassp39728.2021.9413388","title":"Leveraging Acoustic and Linguistic Embeddings from Pretrained Speech and Language Models for Intent Classification","display_name":"Leveraging Acoustic and Linguistic Embeddings from Pretrained Speech and Language Models for Intent Classification","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163044982","doi":"https://doi.org/10.1109/icassp39728.2021.9413388","mag":"3163044982"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413388","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5067433878","display_name":"Bidisha Sharma","orcid":"https://orcid.org/0000-0002-4195-3532"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bidisha Sharma","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048910634","display_name":"Maulik C. Madhavi","orcid":"https://orcid.org/0000-0001-8743-6437"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Maulik Madhavi","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":2.1979,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.90032964,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7498","last_page":"7502"},"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":0.9983999729156494,"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/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":0.8116540312767029},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6991328597068787},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5981430411338806},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.53482985496521},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5264654755592346},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5220230221748352},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5139064788818359},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.47296327352523804},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.43547922372817993},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4282296597957611},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3412106931209564},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0668565034866333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8116540312767029},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6991328597068787},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5981430411338806},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.53482985496521},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5264654755592346},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5220230221748352},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5139064788818359},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.47296327352523804},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.43547922372817993},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4282296597957611},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3412106931209564},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0668565034866333},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413388","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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","score":0.800000011920929,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W648947103","https://openalex.org/W854541894","https://openalex.org/W1649407914","https://openalex.org/W1821462560","https://openalex.org/W1964812476","https://openalex.org/W1972595521","https://openalex.org/W2091671846","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2187089797","https://openalex.org/W2193413348","https://openalex.org/W2327501763","https://openalex.org/W2405622356","https://openalex.org/W2519091744","https://openalex.org/W2545177271","https://openalex.org/W2613904329","https://openalex.org/W2786839803","https://openalex.org/W2894164357","https://openalex.org/W2896457183","https://openalex.org/W2962894366","https://openalex.org/W2963288440","https://openalex.org/W2963341956","https://openalex.org/W2964051877","https://openalex.org/W2964108264","https://openalex.org/W2964265128","https://openalex.org/W2964308564","https://openalex.org/W2970641574","https://openalex.org/W2972463723","https://openalex.org/W2972584841","https://openalex.org/W2972951327","https://openalex.org/W3015885816","https://openalex.org/W3016006013","https://openalex.org/W3016219267","https://openalex.org/W3038268361","https://openalex.org/W3096589040","https://openalex.org/W6623517193","https://openalex.org/W6638523607","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6687566353","https://openalex.org/W6713452507","https://openalex.org/W6737778391","https://openalex.org/W6755207826","https://openalex.org/W6767552790","https://openalex.org/W6773769268"],"related_works":["https://openalex.org/W2126322296","https://openalex.org/W2121652828","https://openalex.org/W3033124456","https://openalex.org/W2955724459","https://openalex.org/W2163537793","https://openalex.org/W2037769829","https://openalex.org/W2916997151","https://openalex.org/W2781555308","https://openalex.org/W2402899696","https://openalex.org/W3021690593"],"abstract_inverted_index":{"Intent":[0],"classification":[1,11,74],"is":[2,13],"a":[3,17,21,71,82,92],"task":[4],"in":[5],"spoken":[6],"language":[7,94],"understanding.":[8],"An":[9],"intent":[10,73],"system":[12,39,86],"usually":[14],"implemented":[15],"as":[16,44],"pipeline":[18],"process,":[19],"with":[20],"speech":[22,84,138],"recognition":[23,85],"module":[24],"followed":[25],"by":[26],"text":[27],"processing":[28],"that":[29,40,76],"classifies":[30,47],"the":[31,48,103,125],"intents.":[32,123],"There":[33],"are":[34],"also":[35],"studies":[36],"of":[37,56,112],"end-to-end":[38],"take":[41,54],"acoustic":[42,78,104,114],"features":[43,79,89],"input":[45],"and":[46,60,87,115,131,136],"intents":[49],"directly.":[50],"Such":[51],"systems":[52],"don\u2019t":[53],"advantage":[55],"relevant":[57],"linguistic":[58,88,107,116],"information,":[59],"suffer":[61],"from":[62,81,91],"limited":[63],"training":[64],"data.":[65],"In":[66],"this":[67],"work,":[68],"we":[69,128],"propose":[70],"novel":[72],"framework":[75],"employs":[77],"extracted":[80],"pretrained":[83,93],"learned":[90],"model.":[95],"We":[96,109],"use":[97],"knowledge":[98],"distillation":[99],"technique":[100],"to":[101,121],"map":[102],"embeddings":[105,117],"towards":[106],"embeddings.":[108],"perform":[110],"fusion":[111],"both":[113],"through":[118],"cross-attention":[119],"approach":[120],"classify":[122],"With":[124],"pro-posed":[126],"method,":[127],"achieve":[129],"90.86%":[130],"99.07%":[132],"accuracy":[133],"on":[134],"ATIS":[135],"Fluent":[137],"corpus,":[139],"respectively.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}