{"id":"https://openalex.org/W3217767527","doi":"https://doi.org/10.1109/icassp43922.2022.9747674","title":"ESPnet-SLU: Advancing Spoken Language Understanding Through ESPnet","display_name":"ESPnet-SLU: Advancing Spoken Language Understanding Through ESPnet","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3217767527","doi":"https://doi.org/10.1109/icassp43922.2022.9747674","mag":"3217767527"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747674","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747674","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/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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081451455","display_name":"Pavel Denisov","orcid":null},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Pavel Denisov","raw_affiliation_strings":["University of Stuttgart"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stuttgart","institution_ids":["https://openalex.org/I100066346"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","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":false,"raw_author_name":"Yifan Peng","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074415592","display_name":"Yuekai Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuekai Zhang","raw_affiliation_strings":["Zoom Video Communications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zoom Video Communications","institution_ids":[]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021201726","display_name":"Brian Yan","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":"Brian Yan","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020700841","display_name":"Ngoc Thang Vu","orcid":"https://orcid.org/0000-0001-7893-9147"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ngoc Thang Vu","raw_affiliation_strings":["University of Stuttgart"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stuttgart","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107337645","display_name":"Alan W. Black","orcid":"https://orcid.org/0000-0001-8820-8831"},"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":"Alan W Black","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"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":48,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7167","last_page":"7171"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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/T12031","display_name":"Speech and dialogue systems","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":0.9163979291915894},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.7018060684204102},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.6011262536048889},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5894775390625},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5884298086166382},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.5621373057365417},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4915500581264496},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.468616783618927},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.44519948959350586},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.42487964034080505},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41679757833480835},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3715413808822632},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.19555988907814026},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.13096138834953308}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9163979291915894},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.7018060684204102},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.6011262536048889},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5894775390625},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5884298086166382},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.5621373057365417},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4915500581264496},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.468616783618927},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.44519948959350586},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.42487964034080505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41679757833480835},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3715413808822632},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.19555988907814026},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.13096138834953308}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747674","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747674","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":0.75,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":77,"referenced_works":["https://openalex.org/W1989271290","https://openalex.org/W2128970689","https://openalex.org/W2146334809","https://openalex.org/W2166637769","https://openalex.org/W2171144711","https://openalex.org/W2559260703","https://openalex.org/W2739936944","https://openalex.org/W2766219058","https://openalex.org/W2797583228","https://openalex.org/W2803609229","https://openalex.org/W2805479865","https://openalex.org/W2896457183","https://openalex.org/W2917937435","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2951910991","https://openalex.org/W2962745521","https://openalex.org/W2962756109","https://openalex.org/W2962780374","https://openalex.org/W2962803631","https://openalex.org/W2963341956","https://openalex.org/W2963968160","https://openalex.org/W2964331270","https://openalex.org/W2971351151","https://openalex.org/W2972430654","https://openalex.org/W2972541922","https://openalex.org/W2972818416","https://openalex.org/W2979826702","https://openalex.org/W2981269614","https://openalex.org/W3007328579","https://openalex.org/W3016160783","https://openalex.org/W3016473712","https://openalex.org/W3017650141","https://openalex.org/W3025165719","https://openalex.org/W3036601975","https://openalex.org/W3037057938","https://openalex.org/W3037217258","https://openalex.org/W3041561163","https://openalex.org/W3092368332","https://openalex.org/W3095384101","https://openalex.org/W3096251052","https://openalex.org/W3097286738","https://openalex.org/W3097777922","https://openalex.org/W3098169801","https://openalex.org/W3098824823","https://openalex.org/W3099782249","https://openalex.org/W3100460087","https://openalex.org/W3105163367","https://openalex.org/W3110740243","https://openalex.org/W3143995484","https://openalex.org/W3151851237","https://openalex.org/W3161223924","https://openalex.org/W3167533889","https://openalex.org/W3169320628","https://openalex.org/W3176896803","https://openalex.org/W3197314576","https://openalex.org/W3197580070","https://openalex.org/W3197674197","https://openalex.org/W3197697656","https://openalex.org/W3198361190","https://openalex.org/W3198429080","https://openalex.org/W3198555173","https://openalex.org/W3198594919","https://openalex.org/W3209059054","https://openalex.org/W4287596060","https://openalex.org/W4297683418","https://openalex.org/W6741704050","https://openalex.org/W6750665317","https://openalex.org/W6751425476","https://openalex.org/W6752049284","https://openalex.org/W6755207826","https://openalex.org/W6755871579","https://openalex.org/W6776148200","https://openalex.org/W6779919476","https://openalex.org/W6780218876","https://openalex.org/W6784579990","https://openalex.org/W6785224828"],"related_works":["https://openalex.org/W2404510748","https://openalex.org/W3089218859","https://openalex.org/W3174008653","https://openalex.org/W4288099861","https://openalex.org/W2893411096","https://openalex.org/W4224919006","https://openalex.org/W4213400064","https://openalex.org/W4390690247","https://openalex.org/W2139439365","https://openalex.org/W2003020325"],"abstract_inverted_index":{"As":[0],"Automatic":[1],"Speech":[2,115,118],"Processing":[3,24],"(ASR)":[4],"systems":[5],"are":[6,29],"getting":[7],"better,":[8],"there":[9,28,50],"is":[10,51,76,90,100,164],"an":[11,56],"increasing":[12],"interest":[13],"of":[14,81],"using":[15],"the":[16,123,158],"ASR":[17,139],"output":[18],"to":[19,38,54,64,114,125,135],"do":[20],"downstream":[21],"Natural":[22],"Language":[23,45],"(NLP)":[25],"tasks.":[26],"However,":[27],"few":[30],"open":[31,57],"source":[32,58],"toolkits":[33],"that":[34,60,132,152],"can":[35,61,153],"be":[36,62],"used":[37,63,103],"generate":[39],"reproducible":[40],"results":[41],"on":[42],"different":[43,138],"Spoken":[44],"Understanding":[46],"(SLU)":[47],"benchmarks.":[48],"Hence,":[49],"a":[52,66,86,91,101],"need":[53],"build":[55],"standard":[59,105],"have":[65],"faster":[67],"start":[68],"into":[69],"SLU":[70,130],"research.":[71],"We":[72,121,143],"present":[73],"ESPnet-SLU,":[74],"which":[75,99],"designed":[77],"for":[78,106,128],"quick":[79],"development":[80],"spoken":[82],"language":[83],"understanding":[84],"in":[85],"single":[87],"framework.":[88],"ESPnet-SLU":[89],"project":[92],"inside":[93],"end-to-end":[94],"speech":[95,108],"processing":[96,109],"toolkit,":[97],"ESPnet,":[98],"widely":[102],"open-source":[104],"various":[107,129],"tasks":[110],"like":[111],"ASR,":[112],"Text":[113],"(TTS)":[116],"and":[117,140],"Translation":[119],"(ST).":[120],"enhance":[122],"toolkit":[124,163],"provide":[126,145],"implementations":[127],"benchmarks":[131],"enable":[133],"researchers":[134],"seamlessly":[136],"mix-and-match":[137],"NLU":[141],"models.":[142],"also":[144],"pretrained":[146],"models":[147],"with":[148],"intensively":[149],"tuned":[150],"hyper-parameters":[151],"match":[154],"or":[155],"even":[156],"outperform":[157],"current":[159],"state-of-the-art":[160],"performances.":[161],"The":[162],"publicly":[165],"available":[166],"at":[167],"https://github.com/espnet/espnet.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}