{"id":"https://openalex.org/W4388624002","doi":"https://doi.org/10.1109/ro-man57019.2023.10309475","title":"SGGNet<sup>2</sup>: Speech-Scene Graph Grounding Network for Speech-guided Navigation","display_name":"SGGNet<sup>2</sup>: Speech-Scene Graph Grounding Network for Speech-guided Navigation","publication_year":2023,"publication_date":"2023-08-28","ids":{"openalex":"https://openalex.org/W4388624002","doi":"https://doi.org/10.1109/ro-man57019.2023.10309475"},"language":"en","primary_location":{"id":"doi:10.1109/ro-man57019.2023.10309475","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man57019.2023.10309475","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","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/A5100331512","display_name":"Dohyun Kim","orcid":"https://orcid.org/0000-0002-6069-2032"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dohyun Kim","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,Robust Intelligence and Robotics (RIRO) laboratory,Korea","Robust Intelligence and Robotics (RIRO) laboratory, Korea Advanced Institute of Science and Technology, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,Robust Intelligence and Robotics (RIRO) laboratory,Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Robust Intelligence and Robotics (RIRO) laboratory, Korea Advanced Institute of Science and Technology, Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006794003","display_name":"Yeseung Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yeseung Kim","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,Robust Intelligence and Robotics (RIRO) laboratory,Korea","Robust Intelligence and Robotics (RIRO) laboratory, Korea Advanced Institute of Science and Technology, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,Robust Intelligence and Robotics (RIRO) laboratory,Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Robust Intelligence and Robotics (RIRO) laboratory, Korea Advanced Institute of Science and Technology, Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102771686","display_name":"Jaehwi Jang","orcid":"https://orcid.org/0009-0007-4850-0679"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaehwi Jang","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,Robust Intelligence and Robotics (RIRO) laboratory,Korea","Robust Intelligence and Robotics (RIRO) laboratory, Korea Advanced Institute of Science and Technology, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,Robust Intelligence and Robotics (RIRO) laboratory,Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Robust Intelligence and Robotics (RIRO) laboratory, Korea Advanced Institute of Science and Technology, Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088914344","display_name":"Minjae Song","orcid":"https://orcid.org/0009-0001-7761-0734"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minjae Song","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,Robust Intelligence and Robotics (RIRO) laboratory,Korea","Robust Intelligence and Robotics (RIRO) laboratory, Korea Advanced Institute of Science and Technology, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,Robust Intelligence and Robotics (RIRO) laboratory,Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Robust Intelligence and Robotics (RIRO) laboratory, Korea Advanced Institute of Science and Technology, Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107936974","display_name":"Woojin Choi","orcid":"https://orcid.org/0000-0002-5886-8836"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Woojin Choi","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,Robust Intelligence and Robotics (RIRO) laboratory,Korea","Robust Intelligence and Robotics (RIRO) laboratory, Korea Advanced Institute of Science and Technology, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,Robust Intelligence and Robotics (RIRO) laboratory,Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Robust Intelligence and Robotics (RIRO) laboratory, Korea Advanced Institute of Science and Technology, Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074295573","display_name":"Daehyung Park","orcid":"https://orcid.org/0000-0002-1287-9433"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Daehyung Park","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,Robust Intelligence and Robotics (RIRO) laboratory,Korea","Robust Intelligence and Robotics (RIRO) laboratory, Korea Advanced Institute of Science and Technology, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,Robust Intelligence and Robotics (RIRO) laboratory,Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Robust Intelligence and Robotics (RIRO) laboratory, Korea Advanced Institute of Science and Technology, Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1648","last_page":"1654"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991999864578247,"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":0.9991999864578247,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9983000159263611,"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":0.8121353387832642},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.611832320690155},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5499384999275208},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5134716629981995},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.505462646484375},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4798564314842224},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.47818616032600403},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.44111430644989014},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.42612218856811523},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38452500104904175},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07359844446182251}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8121353387832642},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.611832320690155},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5499384999275208},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5134716629981995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.505462646484375},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4798564314842224},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.47818616032600403},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.44111430644989014},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.42612218856811523},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38452500104904175},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07359844446182251},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ro-man57019.2023.10309475","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man57019.2023.10309475","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2007820193","https://openalex.org/W2127141656","https://openalex.org/W2196984578","https://openalex.org/W2236233024","https://openalex.org/W2327501763","https://openalex.org/W2799268915","https://openalex.org/W2936774411","https://openalex.org/W2963037989","https://openalex.org/W2963166639","https://openalex.org/W2967955574","https://openalex.org/W2972756321","https://openalex.org/W2980799546","https://openalex.org/W2984375830","https://openalex.org/W3001273258","https://openalex.org/W3091195047","https://openalex.org/W3091427154","https://openalex.org/W3095974555","https://openalex.org/W3097777922","https://openalex.org/W3107521863","https://openalex.org/W3122295921","https://openalex.org/W4210423514","https://openalex.org/W4224912544","https://openalex.org/W4226361680","https://openalex.org/W4312301659","https://openalex.org/W4322704448","https://openalex.org/W6726497184","https://openalex.org/W6731800901","https://openalex.org/W6755702254","https://openalex.org/W6757817989"],"related_works":["https://openalex.org/W2021787609","https://openalex.org/W2097328689","https://openalex.org/W4234899305","https://openalex.org/W1537063595","https://openalex.org/W2379604501","https://openalex.org/W2373854414","https://openalex.org/W2522183581","https://openalex.org/W2954371137","https://openalex.org/W2120744156","https://openalex.org/W1940530101"],"abstract_inverted_index":{"The":[0],"spoken":[1,56],"language":[2,24],"serves":[3],"as":[4],"an":[5],"accessible":[6],"and":[7,12,38,66,132],"efficient":[8],"interface,":[9],"enabling":[10],"non-experts":[11],"disabled":[13],"users":[14],"to":[15,31],"interact":[16],"with":[17,92],"complex":[18],"assistant":[19],"robots.":[20],"However,":[21],"accurately":[22],"grounding":[23,50,85,89,113,129],"utterances":[25,57],"gives":[26],"a":[27,46,143,148],"significant":[28],"challenge":[29],"due":[30],"the":[32,60,78,87,93,104,111,119,138],"acoustic":[33,61,79],"variability":[34],"in":[35,128,142],"speakers\u2019":[36],"voices":[37],"environmental":[39],"noise.":[40],"In":[41],"this":[42,101],"work,":[43],"we":[44,81],"propose":[45],"novel":[47],"speech-scene":[48],"graph":[49],"network":[51,90,114],"(SGGNet2)":[52],"that":[53],"robustly":[54],"grounds":[55],"by":[58,102],"leveraging":[59],"similarity":[62],"between":[63],"correctly":[64],"recognized":[65],"misrecognized":[67],"words":[68],"obtained":[69],"from":[70,96,153],"automatic":[71],"speech":[72,108,126],"recognition":[73],"(ASR)":[74],"systems.":[75],"To":[76],"incorporate":[77],"similarity,":[80],"extend":[82],"our":[83],"previous":[84],"model,":[86],"scene-graph-based":[88],"(SGGNet),":[91],"ASR":[94],"model":[95],"NVIDIA":[97],"NeMo.":[98],"We":[99,117,135],"accomplish":[100],"feeding":[103],"latent":[105,123],"vector":[106],"of":[107,121,125,140],"pronunciations":[109],"into":[110],"BERT-based":[112],"within":[115],"SGGNet.":[116],"evaluate":[118],"effectiveness":[120],"using":[122,147],"vectors":[124],"commands":[127],"through":[130],"qualitative":[131],"quantitative":[133],"studies.":[134],"also":[136],"demonstrate":[137],"capability":[139],"SGGNet2":[141],"speech-based":[144],"navigation":[145],"task":[146],"real":[149],"quadruped":[150],"robot,":[151],"RBQ-3,":[152],"Rainbow":[154],"Robotics.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
