{"id":"https://openalex.org/W4372341986","doi":"https://doi.org/10.1109/icassp49357.2023.10096795","title":"End-to-End Spoken Language Understanding Using Joint CTC Loss and Self-Supervised, Pretrained Acoustic Encoders","display_name":"End-to-End Spoken Language Understanding Using Joint CTC Loss and Self-Supervised, Pretrained Acoustic Encoders","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372341986","doi":"https://doi.org/10.1109/icassp49357.2023.10096795"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096795","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096795","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/A5063578134","display_name":"Jixuan Wang","orcid":"https://orcid.org/0000-0003-1986-6747"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jixuan Wang","raw_affiliation_strings":["Amazon Alexa AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023415990","display_name":"Martin Radfar","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Radfar","raw_affiliation_strings":["Amazon Alexa AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101693020","display_name":"Kai Wei","orcid":"https://orcid.org/0000-0001-7068-6114"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Wei","raw_affiliation_strings":["Amazon Alexa AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081001199","display_name":"Clement Chung","orcid":"https://orcid.org/0000-0002-7189-6612"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Clement Chung","raw_affiliation_strings":["Amazon Alexa AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"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/T10860","display_name":"Speech and Audio Processing","score":0.9973000288009644,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8472139835357666},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7656689882278442},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6569641828536987},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6327680349349976},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6187497973442078},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6027070879936218},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5532922148704529},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5210320949554443},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5139017105102539},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4764140844345093},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.43879997730255127},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4332769513130188},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.4324203133583069},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4152878522872925},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.21450158953666687},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09156179428100586}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8472139835357666},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7656689882278442},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6569641828536987},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6327680349349976},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6187497973442078},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6027070879936218},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5532922148704529},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5210320949554443},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5139017105102539},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4764140844345093},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.43879997730255127},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4332769513130188},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.4324203133583069},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4152878522872925},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.21450158953666687},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09156179428100586},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096795","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096795","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1649407914","https://openalex.org/W1828163288","https://openalex.org/W1972595521","https://openalex.org/W2153962611","https://openalex.org/W2251058040","https://openalex.org/W2327501763","https://openalex.org/W2797583228","https://openalex.org/W2891229414","https://openalex.org/W2894164357","https://openalex.org/W2899663614","https://openalex.org/W2963288440","https://openalex.org/W2972584841","https://openalex.org/W3036601975","https://openalex.org/W3049038774","https://openalex.org/W3095552229","https://openalex.org/W3097964672","https://openalex.org/W3098169801","https://openalex.org/W3100460087","https://openalex.org/W3155162503","https://openalex.org/W3161302809","https://openalex.org/W3179843342","https://openalex.org/W3208743843","https://openalex.org/W3209059054","https://openalex.org/W3217767527","https://openalex.org/W4225313540","https://openalex.org/W4226442948","https://openalex.org/W4246962055","https://openalex.org/W4296070421","https://openalex.org/W6638749077","https://openalex.org/W6750665317","https://openalex.org/W6755977528","https://openalex.org/W6780218876","https://openalex.org/W6802609832"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W1761388607","https://openalex.org/W2038083449","https://openalex.org/W1997922073","https://openalex.org/W3177678247","https://openalex.org/W157723669","https://openalex.org/W2284708545"],"abstract_inverted_index":{"It":[0],"is":[1],"challenging":[2],"to":[3,17,35,41,65],"extract":[4,36,66],"semantic":[5],"meanings":[6],"directly":[7],"from":[8],"audio":[9],"signals":[10],"in":[11],"spoken":[12],"language":[13],"understanding":[14],"(SLU),":[15],"due":[16],"the":[18,90,91,99,107,112],"lack":[19],"of":[20],"textual":[21,37,67],"information.":[22],"Popular":[23],"end-to-end":[24],"(E2E)":[25],"SLU":[26,74,78,109],"models":[27,34],"utilize":[28],"sequence-to-sequence":[29],"automatic":[30],"speech":[31],"recognition":[32],"(ASR)":[33],"embeddings":[38,68],"as":[39],"input":[40],"infer":[42],"semantics,":[43],"which,":[44],"however,":[45],"require":[46],"computationally":[47],"expensive":[48],"auto-regressive":[49],"decoding.":[50],"In":[51],"this":[52],"work,":[53],"we":[54],"leverage":[55],"self-supervised":[56],"acoustic":[57],"encoders":[58],"fine-tuned":[59],"with":[60],"Connectionist":[61],"Temporal":[62],"Classification":[63],"(CTC)":[64],"and":[69,73,102],"use":[70],"joint":[71],"CTC":[72],"losses":[75],"for":[76],"utterance-level":[77],"tasks.":[79],"Experiments":[80],"show":[81],"that":[82],"our":[83],"model":[84,97,110],"achieves":[85],"4%":[86],"absolute":[87,104],"improvement":[88,105],"over":[89,106],"state-of-theart":[92],"(SOTA)":[93],"dialogue":[94],"act":[95],"classification":[96],"on":[98,111],"DSTC2":[100],"dataset":[101],"1.3%":[103],"SOTA":[108],"SLURP":[113],"dataset.":[114]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}