{"id":"https://openalex.org/W4385822549","doi":"https://doi.org/10.21437/interspeech.2023-2262","title":"Multimodal Speech Recognition for Language-Guided Embodied Agents","display_name":"Multimodal Speech Recognition for Language-Guided Embodied Agents","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822549","doi":"https://doi.org/10.21437/interspeech.2023-2262"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-2262","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-2262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5109585531","display_name":"Allen Y. Chang","orcid":"https://orcid.org/0000-0003-1195-1728"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Allen Chang","raw_affiliation_strings":["Department of Computer Science, University of Southern California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018650811","display_name":"Xiaoyuan Zhu","orcid":"https://orcid.org/0000-0002-6365-0997"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoyuan Zhu","raw_affiliation_strings":["Center for Artificial Intelligence in Society, University of Southern California, USA","Department of Computer Science, University of Southern California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence in Society, University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Department of Computer Science, University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091019630","display_name":"Aarav Monga","orcid":"https://orcid.org/0000-0002-0806-125X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aarav Monga","raw_affiliation_strings":["Center for Artificial Intelligence in Society, University of Southern California, USA","Department of Computer Science, University of Southern California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence in Society, University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Department of Computer Science, University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027188711","display_name":"Seoho Ahn","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seoho Ahn","raw_affiliation_strings":["Department of Computer Science, University of Southern California, USA","Center for Artificial Intelligence in Society, University of Southern California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Center for Artificial Intelligence in Society, University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082028315","display_name":"Tejas Srinivasan","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tejas Srinivasan","raw_affiliation_strings":["Department of Computer Science, University of Southern California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108062941","display_name":"Jesse Thomason","orcid":"https://orcid.org/0000-0001-9199-0633"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jesse Thomason","raw_affiliation_strings":["Department of Computer Science, University of Southern California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5109585531"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1608","last_page":"1612"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9984999895095825,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983999729156494,"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":0.8650075197219849},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6756124496459961},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6662406325340271},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.6632956266403198},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.6450076699256897},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5693743228912354},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5674614906311035},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5418722033500671},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5005283355712891},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.4725898206233978},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44182658195495605}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8650075197219849},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6756124496459961},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6662406325340271},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.6632956266403198},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.6450076699256897},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5693743228912354},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5674614906311035},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5418722033500671},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5005283355712891},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4725898206233978},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44182658195495605},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-2262","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-2262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4099999964237213,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W124086577","https://openalex.org/W1494198834","https://openalex.org/W2113786253","https://openalex.org/W2512544816","https://openalex.org/W2762590475","https://openalex.org/W2799002257","https://openalex.org/W2899274165","https://openalex.org/W2959918500","https://openalex.org/W2962866381","https://openalex.org/W2963360627","https://openalex.org/W2963800628","https://openalex.org/W2964182350","https://openalex.org/W2971077754","https://openalex.org/W2979727876","https://openalex.org/W3015678833","https://openalex.org/W3034578524","https://openalex.org/W3034758614","https://openalex.org/W3036601975","https://openalex.org/W3099041253","https://openalex.org/W3099414366","https://openalex.org/W3100923070","https://openalex.org/W3108332675","https://openalex.org/W3166396011","https://openalex.org/W3182074706","https://openalex.org/W3203663566","https://openalex.org/W4214700710","https://openalex.org/W4221167437","https://openalex.org/W4286905705","https://openalex.org/W4287079536","https://openalex.org/W4287634588","https://openalex.org/W4288297863","https://openalex.org/W4320536390"],"related_works":["https://openalex.org/W2380179524","https://openalex.org/W4283365723","https://openalex.org/W2963001125","https://openalex.org/W2091233881","https://openalex.org/W2352366064","https://openalex.org/W4250820896","https://openalex.org/W2124102101","https://openalex.org/W4250305970","https://openalex.org/W1484550171","https://openalex.org/W2333383158"],"abstract_inverted_index":{"Benchmarks":[0],"for":[1,123],"language-guided":[2,125],"embodied":[3,126],"agents":[4,11],"typically":[5],"assume":[6],"text-based":[7],"instructions,":[8,65],"but":[9],"deployed":[10],"will":[12],"encounter":[13],"spoken":[14,53,64,81,109],"instructions.While":[15],"Automatic":[16],"Speech":[17],"Recognition":[18],"(ASR)":[19],"models":[20,95,115],"can":[21,29],"bridge":[22],"the":[23,31,45,68],"input":[24],"gap,":[25],"erroneous":[26],"ASR":[27,41,94,114],"transcripts":[28],"hurt":[30],"agents'":[32],"ability":[33],"to":[34,49,98],"complete":[35],"tasks.We":[36],"propose":[37],"training":[38],"a":[39,60,124],"multimodal":[40,93,113],"model":[42,58],"that":[43,84,108],"utilizes":[44],"accompanying":[46],"visual":[47,86],"context":[48],"reduce":[50],"errors":[51],"in":[52,117],"instruction":[54],"transcripts.We":[55],"train":[56],"our":[57],"on":[59],"dataset":[61],"of":[62],"synthetic":[63],"derived":[66],"from":[67],"ALFRED":[69],"household":[70],"task":[71,119],"dataset,":[72],"where":[73],"we":[74],"simulate":[75],"acoustic":[76],"noise":[77],"by":[78,112],"systematically":[79],"masking":[80],"words.We":[82],"find":[83,107],"utilizing":[85],"observations":[87],"facilitates":[88],"masked":[89,101],"word":[90],"recovery,":[91],"with":[92],"recovering":[96],"up":[97],"30%":[99],"more":[100],"words":[102],"than":[103],"unimodal":[104],"baselines.We":[105],"also":[106],"instructions":[110],"transcribed":[111],"result":[116],"higher":[118],"completion":[120],"success":[121],"rates":[122],"agent.github.com":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2025-10-10T00:00:00"}