{"id":"https://openalex.org/W3098169801","doi":"https://doi.org/10.1109/icassp43922.2022.9747759","title":"Tie Your Embeddings Down: Cross-Modal Latent Spaces for End-to-end Spoken Language Understanding","display_name":"Tie Your Embeddings Down: Cross-Modal Latent Spaces for End-to-end Spoken Language Understanding","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3098169801","doi":"https://doi.org/10.1109/icassp43922.2022.9747759","mag":"3098169801"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747759","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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/A5081661890","display_name":"Bhuvan Agrawal","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":"Bhuvan Agrawal","raw_affiliation_strings":["Amazon,Alexa AI","Alexa AI, Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon,Alexa AI","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Alexa AI, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100706958","display_name":"Markus M\u00fcller","orcid":"https://orcid.org/0000-0003-0907-3583"},"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":"Markus Muller","raw_affiliation_strings":["Amazon,Alexa AI","Alexa AI, Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon,Alexa AI","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Alexa AI, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067594311","display_name":"Samridhi Choudhary","orcid":"https://orcid.org/0000-0003-3706-7260"},"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":"Samridhi Choudhary","raw_affiliation_strings":["Amazon,Alexa AI","Alexa AI, Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon,Alexa AI","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Alexa AI, Amazon","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","Alexa AI, Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon,Alexa AI","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Alexa AI, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029573067","display_name":"Athanasios Mouchtaris","orcid":"https://orcid.org/0000-0001-7583-0189"},"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":"Athanasios Mouchtaris","raw_affiliation_strings":["Amazon,Alexa AI","Alexa AI, Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon,Alexa AI","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Alexa AI, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040080962","display_name":"Ross McGowan","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":"Ross McGowan","raw_affiliation_strings":["Amazon,Alexa AI","Alexa AI, Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon,Alexa AI","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Alexa AI, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062762746","display_name":"Nathan Susanj","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":"Nathan Susanj","raw_affiliation_strings":["Amazon,Alexa AI","Alexa AI, Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon,Alexa AI","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Alexa AI, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074068808","display_name":"Siegfried Kunzmann","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":"Siegfried Kunzmann","raw_affiliation_strings":["Amazon,Alexa AI","Alexa AI, Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon,Alexa AI","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Alexa AI, Amazon","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":24,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7157","last_page":"7161"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7523963451385498},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6552911996841431},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6343501806259155},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6190958023071289},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.6117722988128662},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5168076753616333},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4363490045070648},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4193989932537079},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40267467498779297},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06386646628379822}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7523963451385498},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6552911996841431},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6343501806259155},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6190958023071289},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.6117722988128662},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5168076753616333},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4363490045070648},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4193989932537079},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40267467498779297},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06386646628379822},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer 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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747759","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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":0.8100000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1527575280","https://openalex.org/W2075085977","https://openalex.org/W2096733369","https://openalex.org/W2099471712","https://openalex.org/W2100799972","https://openalex.org/W2123024445","https://openalex.org/W2184188583","https://openalex.org/W2605572715","https://openalex.org/W2765440071","https://openalex.org/W2774267535","https://openalex.org/W2786839803","https://openalex.org/W2891229414","https://openalex.org/W2894164357","https://openalex.org/W2896457183","https://openalex.org/W2898771141","https://openalex.org/W2914417638","https://openalex.org/W2928075308","https://openalex.org/W2963288440","https://openalex.org/W2963341956","https://openalex.org/W2963389687","https://openalex.org/W2972314145","https://openalex.org/W2972327934","https://openalex.org/W2972525948","https://openalex.org/W2972584841","https://openalex.org/W2980282514","https://openalex.org/W3016006013","https://openalex.org/W3095552229","https://openalex.org/W3096851323","https://openalex.org/W3099206234","https://openalex.org/W3176896803","https://openalex.org/W6755207826","https://openalex.org/W6755871579"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W2562096895","https://openalex.org/W2333799855","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2351687372","https://openalex.org/W4307784074"],"abstract_inverted_index":{"End-to-end":[0],"(E2E)":[1],"spoken":[2,13],"language":[3],"understanding":[4],"(SLU)":[5],"systems":[6],"can":[7],"infer":[8],"the":[9,31,74,88,92,104,109,132],"semantics":[10],"of":[11,33,140,154],"a":[12,26,46,60,67,97,137,147,151,157],"utterance":[14],"directly":[15],"from":[16],"an":[17,22,42,143],"audio":[18,50],"signal.":[19],"However,":[20],"training":[21],"E2E":[23,43,116,144],"system":[24,44],"remains":[25],"challenge,":[27],"largely":[28],"due":[29],"to":[30,85,91],"scarcity":[32],"paired":[34],"audio-semantics":[35],"data.":[36],"In":[37],"this":[38],"paper,":[39],"we":[40],"consider":[41],"as":[45,54],"multi-modal":[47,83],"model,":[48],"with":[49],"and":[51,58,76,118,150],"text":[52,93],"functioning":[53],"its":[55],"two":[56,113],"modalities,":[57],"use":[59],"cross-modal":[61,124,148],"latent":[62,69,105],"space":[63,70,149],"(CMLS)":[64],"architecture,":[65],"where":[66],"shared":[68],"is":[71],"learned":[72],"between":[73],"\u2018acoustic\u2019":[75],"\u2018text\u2019":[77],"embeddings.":[78],"We":[79,107],"propose":[80],"using":[81,162],"different":[82,123],"losses":[84],"explicitly":[86],"align":[87],"acoustic":[89],"embedding":[90],"embeddings":[94],"(obtained":[95],"via":[96],"semantically":[98],"powerful":[99],"pre-trained":[100],"BERT":[101],"model)":[102],"in":[103],"space.":[106],"train":[108],"CMLS":[110,160],"model":[111,145,161],"on":[112,168],"publicly":[114],"available":[115],"datasets":[117],"one":[119],"internal":[120,170],"dataset,":[121],"across":[122],"losses.":[125],"Our":[126],"proposed":[127],"triplet":[128],"loss":[129,167],"function":[130],"achieves":[131,136],"best":[133],"performance.":[134],"It":[135],"relative":[138,152],"improvement":[139,153],"22.1%":[141],"over":[142,156],"without":[146],"2.8%":[155],"previously":[158],"published":[159],"L":[163],"<inf":[164],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[165],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</inf>":[166],"our":[169],"dataset.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}