{"id":"https://openalex.org/W4319862410","doi":"https://doi.org/10.1109/slt54892.2023.10022399","title":"A Study on the Integration of Pre-Trained SSL, ASR, LM and SLU Models for Spoken Language Understanding","display_name":"A Study on the Integration of Pre-Trained SSL, ASR, LM and SLU Models for Spoken Language Understanding","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862410","doi":"https://doi.org/10.1109/slt54892.2023.10022399"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022399","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022399","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5033862822","display_name":"Yifan Peng","orcid":"https://orcid.org/0000-0002-8581-8674"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yifan Peng","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,PA,USA","Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047892839","display_name":"Siddhant Arora","orcid":"https://orcid.org/0000-0003-0375-496X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddhant Arora","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,PA,USA","Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102017467","display_name":"Yosuke Higuchi","orcid":"https://orcid.org/0000-0003-4500-8957"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yosuke Higuchi","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,PA,USA","Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065075209","display_name":"Yushi Ueda","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yushi Ueda","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,PA,USA","Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088696834","display_name":"Sujay V. Kumar","orcid":"https://orcid.org/0000-0001-8797-9482"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sujay Kumar","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,PA,USA","Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083149415","display_name":"K. Ganesan","orcid":"https://orcid.org/0000-0002-4074-0957"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karthik Ganesan","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,PA,USA","Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068873086","display_name":"Siddharth Dalmia","orcid":"https://orcid.org/0000-0003-0437-5988"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddharth Dalmia","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,PA,USA","Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050058892","display_name":"Xuankai Chang","orcid":"https://orcid.org/0000-0002-5221-5412"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuankai Chang","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,PA,USA","Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,PA,USA","Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5033862822"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":1.6982,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.85163977,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"406","last_page":"413"},"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9997000098228455,"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":0.8161836862564087},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.8115344047546387},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6179907321929932},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6071603298187256},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5937484502792358},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5670623183250427},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.54118812084198},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.48287227749824524},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.4828341603279114},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4116745889186859},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38378769159317017}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8161836862564087},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.8115344047546387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6179907321929932},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6071603298187256},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5937484502792358},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5670623183250427},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.54118812084198},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.48287227749824524},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4828341603279114},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4116745889186859},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38378769159317017},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022399","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022399","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2043701535","https://openalex.org/W2058094241","https://openalex.org/W2095705004","https://openalex.org/W2101105183","https://openalex.org/W2128970689","https://openalex.org/W2146334809","https://openalex.org/W2526425061","https://openalex.org/W2739883972","https://openalex.org/W2894164357","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2963288440","https://openalex.org/W2963968160","https://openalex.org/W2971351151","https://openalex.org/W2972584841","https://openalex.org/W2973122799","https://openalex.org/W2979826702","https://openalex.org/W2995181338","https://openalex.org/W3011339933","https://openalex.org/W3041561163","https://openalex.org/W3096109555","https://openalex.org/W3096851323","https://openalex.org/W3097286738","https://openalex.org/W3097777922","https://openalex.org/W3098169801","https://openalex.org/W3100460087","https://openalex.org/W3119308075","https://openalex.org/W3148001440","https://openalex.org/W3161223924","https://openalex.org/W3176896803","https://openalex.org/W3197580070","https://openalex.org/W3197674197","https://openalex.org/W3198587774","https://openalex.org/W3198594919","https://openalex.org/W3198694222","https://openalex.org/W3207558756","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3217767527","https://openalex.org/W4226103796","https://openalex.org/W4287887773","https://openalex.org/W4297683418","https://openalex.org/W4297841571","https://openalex.org/W6631190155","https://openalex.org/W6639829665","https://openalex.org/W6674330103","https://openalex.org/W6751425476","https://openalex.org/W6755207826","https://openalex.org/W6755871579","https://openalex.org/W6766978945","https://openalex.org/W6778490555","https://openalex.org/W6779068807","https://openalex.org/W6780218876","https://openalex.org/W6792221667","https://openalex.org/W6806032124"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2129767422","https://openalex.org/W3210196349","https://openalex.org/W4214728004","https://openalex.org/W2950181282","https://openalex.org/W2963261224","https://openalex.org/W2798287483","https://openalex.org/W2913410650"],"abstract_inverted_index":{"Collecting":[0],"sufficient":[1],"labeled":[2],"data":[3,73],"for":[4,57,126],"spoken":[5],"language":[6,64],"understanding":[7],"(SLU)":[8],"is":[9],"expensive":[10],"and":[11,54,63,78,108,120,130,144],"time-consuming.":[12],"Recent":[13],"studies":[14],"achieved":[15],"promising":[16],"results":[17],"by":[18,26],"using":[19,84],"pre-trained":[20,52,67,87,111,118],"models":[21,53,65,86,112,122,145],"in":[22],"low-resource":[23],"scenarios.":[24],"Inspired":[25],"this,":[27],"we":[28,47],"aim":[29],"to":[30,74,113],"ask:":[31],"which":[32],"(if":[33],"any)":[34],"pre-training":[35],"strategies":[36],"can":[37],"improve":[38],"performance":[39],"across":[40],"SLU":[41,96,104],"benchmarks?":[42],"To":[43],"answer":[44],"this":[45],"question,":[46],"employ":[48],"four":[49],"types":[50],"of":[51,71,152],"their":[55],"combinations":[56],"SLU.":[58],"We":[59,81,98],"leverage":[60],"self-supervised":[61,110],"speech":[62,77,92,121],"(LM)":[66],"on":[68,88,102],"large":[69],"quantities":[70],"un-paired":[72],"extract":[75],"strong":[76],"text":[79],"representations.":[80],"also":[82],"explore":[83],"supervised":[85],"larger":[89],"external":[90],"automatic":[91],"recognition":[93],"(ASR)":[94],"or":[95],"corpora.":[97],"conduct":[99],"extensive":[100],"experiments":[101],"the":[103,127,153],"Evaluation":[105],"(SLUE)":[106],"benchmark":[107],"observe":[109],"be":[114,147],"more":[115],"powerful,":[116],"with":[117],"LM":[119],"being":[123],"most":[124],"beneficial":[125],"Sentiment":[128],"Analysis":[129],"Named":[131],"Entity":[132],"Recognition":[133],"task,":[134],"respectively.":[135],"<sup":[136,139],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[137,140],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[138,141],"Our":[142],"code":[143],"will":[146],"publicly":[148],"available":[149],"as":[150],"part":[151],"ESPnet-SLU":[154],"toolkit.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}