{"id":"https://openalex.org/W4392633862","doi":"https://doi.org/10.1145/3610977.3637473","title":"Dataset and Evaluation of Automatic Speech Recognition for Multi-lingual Intent Recognition on Social Robots","display_name":"Dataset and Evaluation of Automatic Speech Recognition for Multi-lingual Intent Recognition on Social Robots","publication_year":2024,"publication_date":"2024-03-10","ids":{"openalex":"https://openalex.org/W4392633862","doi":"https://doi.org/10.1145/3610977.3637473"},"language":"en","primary_location":{"id":"doi:10.1145/3610977.3637473","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3610977.3637473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM/IEEE International Conference on Human-Robot Interaction","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/A5048597091","display_name":"Antonio Andriella","orcid":"https://orcid.org/0000-0002-6641-6450"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antonio Andriella","raw_affiliation_strings":["Pal Robotics, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0002-6641-6450","affiliations":[{"raw_affiliation_string":"Pal Robotics, Barcelona, Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065709426","display_name":"Raquel Ros","orcid":"https://orcid.org/0000-0002-8295-6932"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raquel Ros","raw_affiliation_strings":["Pal Robotics, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0002-8295-6932","affiliations":[{"raw_affiliation_string":"Pal Robotics, Barcelona, Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094111566","display_name":"Yoav Ellinson","orcid":"https://orcid.org/0009-0001-6116-2869"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yoav Ellinson","raw_affiliation_strings":["Bar-Ilan University, Tel-Aviv, Israel"],"raw_orcid":"https://orcid.org/0009-0001-6116-2869","affiliations":[{"raw_affiliation_string":"Bar-Ilan University, Tel-Aviv, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001052072","display_name":"Sharon Gannot","orcid":"https://orcid.org/0000-0002-2885-170X"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Sharon Gannot","raw_affiliation_strings":["Bar-Ilan University, Tel-Aviv, Israel"],"raw_orcid":"https://orcid.org/0000-0002-2885-170X","affiliations":[{"raw_affiliation_string":"Bar-Ilan University, Tel-Aviv, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074580437","display_name":"S\u00e9verin Lemaignan","orcid":"https://orcid.org/0000-0002-3391-8876"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S\u00e9verin Lemaignan","raw_affiliation_strings":["PAL Robotics, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0002-3391-8876","affiliations":[{"raw_affiliation_string":"PAL Robotics, Barcelona, Spain","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"865","last_page":"869"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9937999844551086,"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":0.7378106117248535},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7210786938667297},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5351831316947937},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3990704417228699},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3977181911468506}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7378106117248535},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7210786938667297},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5351831316947937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3990704417228699},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3977181911468506}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3610977.3637473","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3610977.3637473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:share.osf.io:f547a8d5-73bc-4339-a870-12c454393b0d","is_oa":false,"landing_page_url":"https://osf.io/5kh8g","pdf_url":null,"source":{"id":"https://openalex.org/S4306401127","display_name":"OSF Preprints (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Project"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1338848725","display_name":null,"funder_award_id":"801342","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G6576625896","display_name":null,"funder_award_id":"871245","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2920816696","https://openalex.org/W3094531461","https://openalex.org/W3135282443","https://openalex.org/W3208248887","https://openalex.org/W4323536951"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W3204019825"],"abstract_inverted_index":{"While":[0],"Automatic":[1],"Speech":[2,52],"Recognition":[3],"(ASR)":[4],"systems":[5,48],"excel":[6],"in":[7,12,37],"controlled":[8],"environments,":[9],"challenges":[10],"arise":[11],"robot-specific":[13],"setups":[14],"due":[15],"to":[16],"unique":[17],"microphone":[18],"requirements":[19],"and":[20,41,53,74],"added":[21],"noise":[22],"sources.":[23],"In":[24],"this":[25],"paper,":[26],"we":[27,42,59,83],"create":[28],"a":[29,101],"dataset":[30],"of":[31],"initiating":[32],"conversations":[33],"with":[34,92],"brief":[35],"exchanges":[36],"5":[38],"European":[39],"languages,":[40],"systematically":[43],"evaluate":[44],"current":[45],"state-of-art":[46],"ASR":[47],"(Vosk,":[49],"OpenWhisper,":[50],"Google":[51],"NVidia":[54],"Riva).":[55],"Besides":[56],"standard":[57],"metrics,":[58],"also":[60],"look":[61],"at":[62],"two":[63],"critical":[64],"downstream":[65],"tasks":[66],"for":[67],"human-robot":[68],"verbal":[69],"interaction:":[70],"intent":[71],"recognition":[72],"rate":[73],"entity":[75],"extraction,":[76],"using":[77],"the":[78,98],"open-source":[79,86],"Rasa":[80],"chatbot.":[81],"Overall,":[82],"found":[84],"that":[85],"solutions":[87,94],"as":[88],"Vosk":[89],"performs":[90],"competitively":[91],"closed-source":[93],"while":[95],"running":[96],"on":[97,100],"edge,":[99],"low":[102],"compute":[103],"budget":[104],"(CPU":[105],"only).":[106]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
